上传文件至「py」
This commit is contained in:
@@ -0,0 +1,469 @@
|
|||||||
|
import cheerio from 'assets://js/lib/cheerio.min.js';
|
||||||
|
|
||||||
|
const appConfig = {
|
||||||
|
siteName: "伦理专题影片",
|
||||||
|
siteUrl: "http://yoxayg.com"
|
||||||
|
};
|
||||||
|
const UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36";
|
||||||
|
|
||||||
|
async function init(ext) {
|
||||||
|
console.log("初始化爬虫:", appConfig.siteName);
|
||||||
|
}
|
||||||
|
|
||||||
|
const classList = [
|
||||||
|
{ type_id: "1", type_name: "电影" },
|
||||||
|
{ type_id: "2", type_name: "电视剧" },
|
||||||
|
{ type_id: "3", type_name: "综艺" },
|
||||||
|
{ type_id: "4", type_name: "动漫" },
|
||||||
|
{ type_id: "36", type_name: "短剧" },
|
||||||
|
{ type_id: "6", type_name: "动作片" },
|
||||||
|
{ type_id: "7", type_name: "喜剧片" },
|
||||||
|
{ type_id: "8", type_name: "爱情片" },
|
||||||
|
{ type_id: "9", type_name: "科幻片" },
|
||||||
|
{ type_id: "10", type_name: "恐怖片" },
|
||||||
|
{ type_id: "11", type_name: "剧情片" },
|
||||||
|
{ type_id: "12", type_name: "战争片" },
|
||||||
|
{ type_id: "20", type_name: "记录片" },
|
||||||
|
{ type_id: "34", type_name: "伦理片" },
|
||||||
|
{ type_id: "13", type_name: "国产剧" },
|
||||||
|
{ type_id: "14", type_name: "香港剧" },
|
||||||
|
{ type_id: "15", type_name: "韩国剧" },
|
||||||
|
{ type_id: "16", type_name: "欧美剧" },
|
||||||
|
{ type_id: "21", type_name: "台湾剧" },
|
||||||
|
{ type_id: "22", type_name: "日本剧" },
|
||||||
|
{ type_id: "23", type_name: "海外剧" },
|
||||||
|
{ type_id: "24", type_name: "泰国剧" },
|
||||||
|
{ type_id: "25", type_name: "大陆综艺" },
|
||||||
|
{ type_id: "26", type_name: "港台综艺" },
|
||||||
|
{ type_id: "27", type_name: "日韩综艺" },
|
||||||
|
{ type_id: "28", type_name: "欧美综艺" },
|
||||||
|
{ type_id: "29", type_name: "国产动漫" },
|
||||||
|
{ type_id: "30", type_name: "日韩动漫" },
|
||||||
|
{ type_id: "31", type_name: "欧美动漫" },
|
||||||
|
{ type_id: "32", type_name: "港台动漫" },
|
||||||
|
{ type_id: "33", type_name: "海外动漫" }
|
||||||
|
];
|
||||||
|
|
||||||
|
const typeSlugMap = {
|
||||||
|
"1": "dianying", "2": "dianshiju", "3": "zongyi", "4": "dongman", "6": "dongzuopian",
|
||||||
|
"7": "xijupian", "8": "aiqingpian", "9": "kehuanpian", "10": "kongbupian", "11": "juqingpian",
|
||||||
|
"12": "zhanzhengpian", "13": "guochanju", "14": "xianggangju", "15": "hanguoju", "16": "oumeiju",
|
||||||
|
"20": "jilupian", "21": "taiwanju", "22": "ribenju", "23": "haiwaiju", "24": "taiguoju",
|
||||||
|
"25": "daluzongyi", "26": "gangtaizongyi", "27": "rihanzongyi", "28": "oumeizongyi",
|
||||||
|
"29": "guochandongman", "30": "rihandongman", "31": "oumeidongman", "32": "gangtaidongman",
|
||||||
|
"33": "haiwaidongman", "34": "lunlipian", "36": "duanju"
|
||||||
|
};
|
||||||
|
|
||||||
|
const typeParentMap = {
|
||||||
|
"1": 0, "2": 0, "3": 0, "4": 0, "6": 1, "7": 1, "8": 1, "9": 1, "10": 1,
|
||||||
|
"11": 1, "12": 1, "13": 2, "14": 2, "15": 2, "16": 2, "20": 1, "21": 2, "22": 2,
|
||||||
|
"23": 2, "24": 2, "25": 3, "26": 3, "27": 3, "28": 3, "29": 4, "30": 4,
|
||||||
|
"31": 4, "32": 4, "33": 4, "34": 1, "36": 2
|
||||||
|
};
|
||||||
|
|
||||||
|
function topType(tid) {
|
||||||
|
tid = parseInt(tid || 0, 10);
|
||||||
|
if (tid === 36) return 36;
|
||||||
|
const p = parseInt(typeParentMap[String(tid)] || 0, 10);
|
||||||
|
return p > 0 ? p : tid;
|
||||||
|
}
|
||||||
|
|
||||||
|
function typeSlug(tid) {
|
||||||
|
return typeSlugMap[String(parseInt(tid || 0, 10))] || ('type' + parseInt(tid || 0, 10));
|
||||||
|
}
|
||||||
|
|
||||||
|
function getAreaFilter() {
|
||||||
|
return {
|
||||||
|
"key": "area", "name": "地区", "value": [
|
||||||
|
{ "n": "全部", "v": "" }, { "n": "大陆", "v": "大陆" }, { "n": "香港", "v": "香港" },
|
||||||
|
{ "n": "台湾", "v": "台湾" }, { "n": "美国", "v": "美国" }, { "n": "日本", "v": "日本" },
|
||||||
|
{ "n": "韩国", "v": "韩国" }, { "n": "英国", "v": "英国" }, { "n": "法国", "v": "法国" },
|
||||||
|
{ "n": "德国", "v": "德国" }, { "n": "泰国", "v": "泰国" }, { "n": "印度", "v": "印度" },
|
||||||
|
{ "n": "其他", "v": "其他" }
|
||||||
|
]
|
||||||
|
};
|
||||||
|
}
|
||||||
|
|
||||||
|
function getYearFilter() {
|
||||||
|
let years = [{ "n": "全部", "v": "" }];
|
||||||
|
const currentYear = new Date().getFullYear();
|
||||||
|
for (let y = currentYear; y >= 2010; y--) {
|
||||||
|
years.push({ "n": String(y), "v": String(y) });
|
||||||
|
}
|
||||||
|
return { "key": "year", "name": "年份", "value": years };
|
||||||
|
}
|
||||||
|
|
||||||
|
const commonFilters = [getAreaFilter(), getYearFilter()];
|
||||||
|
|
||||||
|
const myFilters = {};
|
||||||
|
classList.forEach(item => {
|
||||||
|
myFilters[item.type_id] = commonFilters;
|
||||||
|
});
|
||||||
|
|
||||||
|
function fixUrl(u) {
|
||||||
|
if (!u) return '';
|
||||||
|
if (u.startsWith('http')) return u;
|
||||||
|
if (u.startsWith('//')) return 'http:' + u;
|
||||||
|
if (u.startsWith('/')) return appConfig.siteUrl + u;
|
||||||
|
return u;
|
||||||
|
}
|
||||||
|
|
||||||
|
async function home(filter) {
|
||||||
|
let list = [];
|
||||||
|
try {
|
||||||
|
const html = (await req(appConfig.siteUrl, {
|
||||||
|
method: "GET",
|
||||||
|
headers: { "User-Agent": UA }
|
||||||
|
})).content;
|
||||||
|
const $ = cheerio.load(html);
|
||||||
|
let seen = {};
|
||||||
|
|
||||||
|
$(".tpl-card[href]").each(function () {
|
||||||
|
let vod_id = $(this).attr("href");
|
||||||
|
if (!vod_id || seen[vod_id]) return;
|
||||||
|
|
||||||
|
let vod_name = $(this).attr("title") || $(this).find("strong").first().text().trim() || "";
|
||||||
|
vod_name = vod_name.replace(/免费在线观看$/, "");
|
||||||
|
let vod_pic = fixUrl($(this).find("img").first().attr("src") || "");
|
||||||
|
let vod_remarks = $(this).find("em").first().text().trim();
|
||||||
|
|
||||||
|
if (vod_name && vod_id) {
|
||||||
|
seen[vod_id] = true;
|
||||||
|
list.push({ vod_id, vod_name, vod_pic, vod_remarks });
|
||||||
|
}
|
||||||
|
});
|
||||||
|
} catch (e) {
|
||||||
|
console.error("首页推荐获取失败:", e.message);
|
||||||
|
}
|
||||||
|
|
||||||
|
return JSON.stringify({
|
||||||
|
class: classList,
|
||||||
|
filters: myFilters,
|
||||||
|
list: list.slice(0, 30)
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
function buildCategoryUrl(tid, pg, extend) {
|
||||||
|
extend = extend || {};
|
||||||
|
let top = topType(tid);
|
||||||
|
let topSlug = typeSlug(top);
|
||||||
|
let childSlug = (tid != top) ? typeSlug(tid) : '';
|
||||||
|
|
||||||
|
let path;
|
||||||
|
if (childSlug && tid != 36) {
|
||||||
|
path = `/${topSlug}/${childSlug}/`;
|
||||||
|
} else {
|
||||||
|
path = `/${topSlug}/`;
|
||||||
|
}
|
||||||
|
|
||||||
|
if (pg > 1) {
|
||||||
|
path += `page-${pg}.html`;
|
||||||
|
}
|
||||||
|
|
||||||
|
let area = extend.area || '';
|
||||||
|
let year = extend.year || '';
|
||||||
|
if (area || year) {
|
||||||
|
let params = [];
|
||||||
|
if (area) params.push('area=' + encodeURIComponent(area));
|
||||||
|
if (year) params.push('year=' + encodeURIComponent(year));
|
||||||
|
return appConfig.siteUrl + `/api_proxy.php?ac=list&t=${tid}&pg=${pg}&${params.join('&')}`;
|
||||||
|
}
|
||||||
|
|
||||||
|
return appConfig.siteUrl + path;
|
||||||
|
}
|
||||||
|
|
||||||
|
function parseListHtml(html) {
|
||||||
|
const $ = cheerio.load(html);
|
||||||
|
let list = [];
|
||||||
|
let vodIds = {};
|
||||||
|
|
||||||
|
$(".tpl-card.card-poster, .tpl-card.card-wide").each(function () {
|
||||||
|
let $a = $(this);
|
||||||
|
let vod_id = $a.attr("href");
|
||||||
|
if (!vod_id || vodIds[vod_id]) return;
|
||||||
|
|
||||||
|
let vod_name = $a.attr("title") || $a.find("strong").first().text().trim() || "";
|
||||||
|
vod_name = vod_name.replace(/免费在线观看$/, "");
|
||||||
|
let vod_pic = fixUrl($a.find("img").first().attr("src") || "");
|
||||||
|
let vod_remarks = $a.find("em").first().text().trim() || $a.find("small").first().text().trim();
|
||||||
|
|
||||||
|
if (vod_name && vod_id) {
|
||||||
|
vodIds[vod_id] = true;
|
||||||
|
list.push({ vod_id, vod_name, vod_pic, vod_remarks });
|
||||||
|
}
|
||||||
|
});
|
||||||
|
|
||||||
|
if (list.length === 0) {
|
||||||
|
try {
|
||||||
|
let data = JSON.parse(html);
|
||||||
|
if (data.list && Array.isArray(data.list)) {
|
||||||
|
data.list.forEach(item => {
|
||||||
|
let vod_id = `/${typeSlug(topType(item.type_id))}/${(item.vod_en || item.vod_name || '').toLowerCase().replace(/[^a-z0-9]+/g, '')}.html`;
|
||||||
|
let vod_name = item.vod_name || "";
|
||||||
|
let vod_pic = item.vod_pic || "";
|
||||||
|
let vod_remarks = item.vod_remarks || "";
|
||||||
|
if (vod_name) {
|
||||||
|
list.push({ vod_id, vod_name, vod_pic, vod_remarks });
|
||||||
|
}
|
||||||
|
});
|
||||||
|
}
|
||||||
|
} catch (e) {
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let pagecount = 1;
|
||||||
|
$(".pagination a").each(function () {
|
||||||
|
let href = $(this).attr("href") || '';
|
||||||
|
let m = href.match(/page-(\d+)/);
|
||||||
|
if (m) {
|
||||||
|
let p = parseInt(m[1]);
|
||||||
|
if (p > pagecount) pagecount = p;
|
||||||
|
}
|
||||||
|
});
|
||||||
|
|
||||||
|
return { list, pagecount };
|
||||||
|
}
|
||||||
|
|
||||||
|
async function category(tid, pg, filter, extend) {
|
||||||
|
pg = pg || 1;
|
||||||
|
extend = extend || {};
|
||||||
|
|
||||||
|
let url = buildCategoryUrl(tid, pg, extend);
|
||||||
|
|
||||||
|
try {
|
||||||
|
const html = (await req(url, {
|
||||||
|
method: "GET",
|
||||||
|
headers: { "User-Agent": UA, "Referer": appConfig.siteUrl }
|
||||||
|
})).content;
|
||||||
|
const result = parseListHtml(html);
|
||||||
|
return JSON.stringify(result);
|
||||||
|
} catch (e) {
|
||||||
|
console.error("分类列表获取失败:", e.message);
|
||||||
|
return JSON.stringify({ list: [], pagecount: 0 });
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
async function search(wd, quick, page) {
|
||||||
|
page = page || 1;
|
||||||
|
try {
|
||||||
|
const url = `${appConfig.siteUrl}/search-${encodeURIComponent(wd)}${page > 1 ? '-page-' + page : ''}.html`;
|
||||||
|
const html = (await req(url, {
|
||||||
|
method: "GET",
|
||||||
|
headers: { "User-Agent": UA, "Referer": appConfig.siteUrl }
|
||||||
|
})).content;
|
||||||
|
const result = parseListHtml(html);
|
||||||
|
return JSON.stringify(result);
|
||||||
|
} catch (e) {
|
||||||
|
console.error("搜索失败:", e.message);
|
||||||
|
return JSON.stringify({ list: [], pagecount: 0 });
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
async function detail(id) {
|
||||||
|
try {
|
||||||
|
const html = (await req(appConfig.siteUrl + id, {
|
||||||
|
method: "GET",
|
||||||
|
headers: { "User-Agent": UA, "Referer": appConfig.siteUrl }
|
||||||
|
})).content;
|
||||||
|
const $ = cheerio.load(html);
|
||||||
|
|
||||||
|
let vod_name = $("h1").first().text().trim();
|
||||||
|
|
||||||
|
let vod_pic = fixUrl($(".detail-poster img").first().attr("src") || "");
|
||||||
|
|
||||||
|
let vod_director = "";
|
||||||
|
let vod_actor = "";
|
||||||
|
let vod_area = "";
|
||||||
|
let vod_year = "";
|
||||||
|
let vod_content = "";
|
||||||
|
let vod_class = "";
|
||||||
|
let vod_remarks = "";
|
||||||
|
|
||||||
|
$(".detail-tags span").each(function () {
|
||||||
|
let text = $(this).text().trim();
|
||||||
|
if (/^\d{4}$/.test(text) && !vod_year) vod_year = text;
|
||||||
|
else if (/大陆|香港|台湾|美国|日本|韩国|英国|法国|德国|泰国|印度|其他/.test(text) && !vod_area) vod_area = text;
|
||||||
|
else if (!vod_class && text !== vod_year && text !== vod_area && !/更新至|集|期|TC|HD|正片/.test(text)) vod_class = text;
|
||||||
|
});
|
||||||
|
|
||||||
|
vod_remarks = $(".detail-poster span").first().text().trim();
|
||||||
|
|
||||||
|
$(".detail-meta p").each(function () {
|
||||||
|
let text = $(this).text();
|
||||||
|
if (text.includes("主演：") && !vod_actor) {
|
||||||
|
vod_actor = text.replace("主演：", "").trim();
|
||||||
|
}
|
||||||
|
if (text.includes("导演：") && !vod_director) {
|
||||||
|
vod_director = text.replace("导演：", "").trim();
|
||||||
|
}
|
||||||
|
});
|
||||||
|
|
||||||
|
let $intro = $(".detail-intro");
|
||||||
|
if ($intro.length > 0) {
|
||||||
|
vod_content = $intro.first().text().replace("简介：", "").trim();
|
||||||
|
}
|
||||||
|
if (!vod_content) {
|
||||||
|
$intro = $(".article-text");
|
||||||
|
if ($intro.length > 0) {
|
||||||
|
vod_content = $intro.first().text().trim();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let lines = [];
|
||||||
|
let playlists = [];
|
||||||
|
let epArray = [];
|
||||||
|
|
||||||
|
$(".episode-grid a").each(function () {
|
||||||
|
let name = $(this).text().trim();
|
||||||
|
let href = $(this).attr('href') || '';
|
||||||
|
if (name && href) {
|
||||||
|
epArray.push({ name, href });
|
||||||
|
}
|
||||||
|
});
|
||||||
|
|
||||||
|
epArray.sort((a, b) => {
|
||||||
|
let numA = parseInt(a.name.match(/第(\d+)/)?.[1] || 0);
|
||||||
|
let numB = parseInt(b.name.match(/第(\d+)/)?.[1] || 0);
|
||||||
|
return numA - numB;
|
||||||
|
});
|
||||||
|
|
||||||
|
let episodes = epArray.map(ep => `${ep.name}$${ep.href}`);
|
||||||
|
|
||||||
|
if (episodes.length > 0) {
|
||||||
|
lines.push("默认");
|
||||||
|
playlists.push(episodes);
|
||||||
|
} else {
|
||||||
|
let playHref = $(".detail-actions a.btn-primary").attr("href") || "";
|
||||||
|
if (playHref) {
|
||||||
|
lines.push("默认");
|
||||||
|
playlists.push([`正片$${playHref}`]);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if (lines.length === 0) {
|
||||||
|
lines.push("默认");
|
||||||
|
playlists.push([`暂无播放地址$${id}`]);
|
||||||
|
}
|
||||||
|
|
||||||
|
const { vod_play_from, vod_play_url } = buildVodPlayData(lines, playlists);
|
||||||
|
|
||||||
|
return JSON.stringify({
|
||||||
|
list: [{
|
||||||
|
vod_id: id,
|
||||||
|
vod_name,
|
||||||
|
vod_pic,
|
||||||
|
vod_actor,
|
||||||
|
vod_director,
|
||||||
|
vod_remarks,
|
||||||
|
vod_year,
|
||||||
|
vod_area,
|
||||||
|
vod_content,
|
||||||
|
vod_class,
|
||||||
|
vod_play_from,
|
||||||
|
vod_play_url
|
||||||
|
}]
|
||||||
|
});
|
||||||
|
} catch (error) {
|
||||||
|
console.error(`解析详情页异常 [ID: ${id}]:`, error);
|
||||||
|
return JSON.stringify({ list: [] });
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
function buildVodPlayData(lines, playlists) {
|
||||||
|
const processedPlaylists = playlists.map(eps => eps.join('#'));
|
||||||
|
return {
|
||||||
|
vod_play_from: lines.filter(Boolean).join('$$$'),
|
||||||
|
vod_play_url: processedPlaylists.join('$$$')
|
||||||
|
};
|
||||||
|
}
|
||||||
|
|
||||||
|
async function play(flag, id, flags) {
|
||||||
|
try {
|
||||||
|
if (id.startsWith("http")) {
|
||||||
|
return JSON.stringify({
|
||||||
|
parse: 0,
|
||||||
|
Header: { "User-Agent": UA, "Referer": appConfig.siteUrl },
|
||||||
|
url: id
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
const html = (await req(`${appConfig.siteUrl}${id}`, {
|
||||||
|
method: "GET",
|
||||||
|
headers: { "User-Agent": UA, "Referer": appConfig.siteUrl }
|
||||||
|
})).content;
|
||||||
|
|
||||||
|
// 方式1：从 noscript 中提取 m3u8 URL
|
||||||
|
let noscriptMatch = html.match(/<noscript>.*?当前播放地址[：:]\s*(https?:\/\/[^\s<"]+\.m3u8[^\s<"]*)/);
|
||||||
|
if (noscriptMatch) {
|
||||||
|
return JSON.stringify({
|
||||||
|
parse: 0,
|
||||||
|
Header: { "User-Agent": UA, "Referer": appConfig.siteUrl },
|
||||||
|
url: noscriptMatch[1]
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
// 方式2：从 JS 中提取 var src="..."
|
||||||
|
let srcMatch = html.match(/var\s+src\s*=\s*["'](https?:\/\/[^"']+\.m3u8[^"']*)/);
|
||||||
|
if (srcMatch) {
|
||||||
|
return JSON.stringify({
|
||||||
|
parse: 0,
|
||||||
|
Header: { "User-Agent": UA, "Referer": appConfig.siteUrl },
|
||||||
|
url: srcMatch[1]
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
// 方式3：直接匹配 m3u8 URL
|
||||||
|
let urlMatch = html.match(/(https?:\/\/[^"'\s<>]+\.m3u8[^"'\s<>]*)/);
|
||||||
|
if (urlMatch) {
|
||||||
|
return JSON.stringify({
|
||||||
|
parse: 0,
|
||||||
|
Header: { "User-Agent": UA, "Referer": appConfig.siteUrl },
|
||||||
|
url: urlMatch[1]
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
// 方式4：player_aaaa
|
||||||
|
let playerMatch = html.match(/var player_aaaa\s*=\s*(\{.+?\});/);
|
||||||
|
if (playerMatch) {
|
||||||
|
try {
|
||||||
|
let playerData = JSON.parse(playerMatch[1]);
|
||||||
|
if (playerData.url) {
|
||||||
|
return JSON.stringify({
|
||||||
|
parse: 0,
|
||||||
|
Header: { "User-Agent": UA, "Referer": appConfig.siteUrl },
|
||||||
|
url: playerData.url
|
||||||
|
});
|
||||||
|
}
|
||||||
|
} catch (e) {}
|
||||||
|
}
|
||||||
|
|
||||||
|
// 方式5：video 标签的 src
|
||||||
|
const $ = cheerio.load(html);
|
||||||
|
let videoSrc = $("video").attr("src") || $("video source").attr("src");
|
||||||
|
if (videoSrc) {
|
||||||
|
return JSON.stringify({
|
||||||
|
parse: 0,
|
||||||
|
Header: { "User-Agent": UA, "Referer": appConfig.siteUrl },
|
||||||
|
url: fixUrl(videoSrc)
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
return JSON.stringify({
|
||||||
|
parse: 1,
|
||||||
|
Header: { "User-Agent": UA, "Referer": appConfig.siteUrl },
|
||||||
|
url: appConfig.siteUrl + id
|
||||||
|
});
|
||||||
|
} catch (e) {
|
||||||
|
console.error("播放失败:", e);
|
||||||
|
return JSON.stringify({ parse: 0, url: "" });
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
export default {
|
||||||
|
init,
|
||||||
|
home,
|
||||||
|
category,
|
||||||
|
detail,
|
||||||
|
search,
|
||||||
|
play
|
||||||
|
};
|
||||||
@@ -0,0 +1,476 @@
|
|||||||
|
"""
|
||||||
|
@header({
|
||||||
|
searchable: 1,
|
||||||
|
filterable: 1,
|
||||||
|
quickSearch: 1,
|
||||||
|
title: '中央电视台',
|
||||||
|
lang: 'hipy'
|
||||||
|
})
|
||||||
|
"""
|
||||||
|
|
||||||
|
#coding=utf-8
|
||||||
|
#!/usr/bin/python
|
||||||
|
import sys
|
||||||
|
sys.path.append('..')
|
||||||
|
from base.spider import Spider
|
||||||
|
import json
|
||||||
|
import time
|
||||||
|
import base64
|
||||||
|
import re
|
||||||
|
from urllib import request, parse
|
||||||
|
import urllib
|
||||||
|
import urllib.request
|
||||||
|
import time
|
||||||
|
|
||||||
|
class Spider(Spider): # 元类 默认的元类 type
|
||||||
|
def getName(self):
|
||||||
|
return "中央电视台"#可搜索
|
||||||
|
def init(self,extend=""):
|
||||||
|
print("============{0}============".format(extend))
|
||||||
|
pass
|
||||||
|
def destroy(self):
|
||||||
|
pass
|
||||||
|
def isVideoFormat(self,url):
|
||||||
|
pass
|
||||||
|
def manualVideoCheck(self):
|
||||||
|
pass
|
||||||
|
def homeContent(self,filter):
|
||||||
|
result = {}
|
||||||
|
cateManual = {
|
||||||
|
"央视大全":"节目大全",
|
||||||
|
"电视剧": "电视剧",
|
||||||
|
"动画片": "动画片",
|
||||||
|
"纪录片": "纪录片",
|
||||||
|
"特别节目": "特别节目"
|
||||||
|
|
||||||
|
}
|
||||||
|
classes = []
|
||||||
|
for k in cateManual:
|
||||||
|
classes.append({
|
||||||
|
'type_name':k,
|
||||||
|
'type_id':cateManual[k]
|
||||||
|
})
|
||||||
|
result['class'] = classes
|
||||||
|
if(filter):
|
||||||
|
result['filters'] = self.config['filter']
|
||||||
|
return result
|
||||||
|
def homeVideoContent(self):
|
||||||
|
result = {
|
||||||
|
'list':[]
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
def categoryContent(self,tid,pg,filter,extend):
|
||||||
|
result = {}
|
||||||
|
month = ""#月
|
||||||
|
year = ""#年
|
||||||
|
area=''#地区
|
||||||
|
channel=''#频道
|
||||||
|
datafl=''#类型
|
||||||
|
letter=''#字母
|
||||||
|
pagecount=24
|
||||||
|
if tid=='动画片':
|
||||||
|
id=urllib.parse.quote(tid)
|
||||||
|
if 'datadq-area' in extend.keys():
|
||||||
|
area=urllib.parse.quote(extend['datadq-area'])
|
||||||
|
if 'dataszm-letter' in extend.keys():
|
||||||
|
letter=extend['dataszm-letter']
|
||||||
|
if 'datafl-sc' in extend.keys():
|
||||||
|
datafl=urllib.parse.quote(extend['datafl-sc'])
|
||||||
|
url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955899450127&area={0}&sc={4}&fc={1}&letter={2}&p={3}&n=24&serviceId=tvcctv&topv=1&t=json'.format(area,id,letter,pg,datafl)
|
||||||
|
elif tid=='纪录片':
|
||||||
|
id=urllib.parse.quote(tid)
|
||||||
|
if 'datapd-channel' in extend.keys():
|
||||||
|
channel=urllib.parse.quote(extend['datapd-channel'])
|
||||||
|
if 'datafl-sc' in extend.keys():
|
||||||
|
datafl=urllib.parse.quote(extend['datafl-sc'])
|
||||||
|
if 'datanf-year' in extend.keys():
|
||||||
|
year=extend['datanf-year']
|
||||||
|
if 'dataszm-letter' in extend.keys():
|
||||||
|
letter=extend['dataszm-letter']
|
||||||
|
url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955924871139&fc={0}&channel={1}&sc={2}&year={3}&letter={4}&p={5}&n=24&serviceId=tvcctv&topv=1&t=json'.format(id,channel,datafl,year,letter,pg)
|
||||||
|
elif tid=='电视剧':
|
||||||
|
id=urllib.parse.quote(tid)
|
||||||
|
if 'datafl-sc' in extend.keys():
|
||||||
|
datafl=urllib.parse.quote(extend['datafl-sc'])
|
||||||
|
if 'datanf-year' in extend.keys():
|
||||||
|
year=extend['datanf-year']
|
||||||
|
if 'dataszm-letter' in extend.keys():
|
||||||
|
letter=extend['dataszm-letter']
|
||||||
|
url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955853485115&area={0}&sc={1}&fc={2}&year={3}&letter={4}&p={5}&n=24&serviceId=tvcctv&topv=1&t=json'.format(area,datafl,id,year,letter,pg)
|
||||||
|
elif tid=='特别节目':
|
||||||
|
id=urllib.parse.quote(tid)
|
||||||
|
if 'datapd-channel' in extend.keys():
|
||||||
|
channel=urllib.parse.quote(extend['datapd-channel'])
|
||||||
|
if 'datafl-sc' in extend.keys():
|
||||||
|
datafl=urllib.parse.quote(extend['datafl-sc'])
|
||||||
|
if 'dataszm-letter' in extend.keys():
|
||||||
|
letter=extend['dataszm-letter']
|
||||||
|
url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955953877151&channel={0}&sc={1}&fc={2}&bigday=&letter={3}&p={4}&n=24&serviceId=tvcctv&topv=1&t=json'.format(channel,datafl,id,letter,pg)
|
||||||
|
elif tid=='节目大全':
|
||||||
|
cid=''#频道
|
||||||
|
if 'cid' in extend.keys():
|
||||||
|
cid=extend['cid']
|
||||||
|
fc=''#分类
|
||||||
|
if 'fc' in extend.keys():
|
||||||
|
fc=extend['fc']
|
||||||
|
fl=''#字母
|
||||||
|
if 'fl' in extend.keys():
|
||||||
|
fl=extend['fl']
|
||||||
|
url = 'https://api.cntv.cn/lanmu/columnSearch?&fl={0}&fc={1}&cid={2}&p={3}&n=20&serviceId=tvcctv&t=json&cb=ko'.format(fl,fc,cid,pg)
|
||||||
|
pagecount=20
|
||||||
|
else:
|
||||||
|
url = 'https://tv.cctv.com/epg/index.shtml'
|
||||||
|
|
||||||
|
videos=[]
|
||||||
|
htmlText =self.webReadFile(urlStr=url,header=self.header)
|
||||||
|
if tid=='节目大全':
|
||||||
|
index=htmlText.rfind(');')
|
||||||
|
if index>-1:
|
||||||
|
htmlText=htmlText[3:index]
|
||||||
|
videos =self.get_list1(html=htmlText,tid=tid)
|
||||||
|
else:
|
||||||
|
videos =self.get_list(html=htmlText,tid=tid)
|
||||||
|
#print(videos)
|
||||||
|
|
||||||
|
result['list'] = videos
|
||||||
|
result['page'] = pg
|
||||||
|
result['pagecount'] = 9999 if len(videos)>=pagecount else pg
|
||||||
|
result['limit'] = 90
|
||||||
|
result['total'] = 999999
|
||||||
|
return result
|
||||||
|
def detailContent(self,array):
|
||||||
|
result={}
|
||||||
|
aid = array[0].split('###')
|
||||||
|
tid = aid[0]
|
||||||
|
logo = aid[3]
|
||||||
|
lastVideo = aid[2]
|
||||||
|
title = aid[1]
|
||||||
|
id= aid[4]
|
||||||
|
|
||||||
|
vod_year= aid[5]
|
||||||
|
actors= aid[6]
|
||||||
|
brief= aid[7]
|
||||||
|
fromId='CCTV'
|
||||||
|
if tid=="节目大全":
|
||||||
|
lastUrl = 'https://api.cntv.cn/video/videoinfoByGuid?guid={0}&serviceId=tvcctv'.format(id)
|
||||||
|
htmlTxt = self.webReadFile(urlStr=lastUrl,header=self.header)
|
||||||
|
topicId=json.loads(htmlTxt)['ctid']
|
||||||
|
Url = "https://api.cntv.cn/NewVideo/getVideoListByColumn?id={0}&d=&p=1&n=100&sort=desc&mode=0&serviceId=tvcctv&t=json".format(topicId)
|
||||||
|
htmlTxt = self.webReadFile(urlStr=Url,header=self.header)
|
||||||
|
else:
|
||||||
|
Url='https://api.cntv.cn/NewVideo/getVideoListByAlbumIdNew?id={0}&serviceId=tvcctv&p=1&n=100&mode=0&pub=1'.format(id)
|
||||||
|
jRoot = ''
|
||||||
|
videoList = []
|
||||||
|
try:
|
||||||
|
if tid=="搜索":
|
||||||
|
fromId='中央台'
|
||||||
|
videoList=[title+"$"+lastVideo]
|
||||||
|
else:
|
||||||
|
htmlTxt=self.webReadFile(urlStr=Url,header=self.header)
|
||||||
|
jRoot = json.loads(htmlTxt)
|
||||||
|
data=jRoot['data']
|
||||||
|
jsonList=data['list']
|
||||||
|
videoList=self.get_EpisodesList(jsonList=jsonList)
|
||||||
|
if len(videoList)<1:
|
||||||
|
htmlTxt=self.webReadFile(urlStr=lastVideo,header=self.header)
|
||||||
|
if tid=="电视剧" or tid=="纪录片":
|
||||||
|
patternTxt=r"'title':\s*'(?P<title>.+?)',\n{0,1}\s*'brief':\s*'(.+?)',\n{0,1}\s*'img':\s*'(.+?)',\n{0,1}\s*'url':\s*'(?P<url>.+?)'"
|
||||||
|
elif tid=="特别节目":
|
||||||
|
patternTxt=r'class="tp1"><a\s*href="(?P<url>https://.+?)"\s*target="_blank"\s*title="(?P<title>.+?)"></a></div>'
|
||||||
|
elif tid=="动画片":
|
||||||
|
patternTxt=r"'title':\s*'(?P<title>.+?)',\n{0,1}\s*'img':\s*'(.+?)',\n{0,1}\s*'brief':\s*'(.+?)',\n{0,1}\s*'url':\s*'(?P<url>.+?)'"
|
||||||
|
elif tid=="节目大全":
|
||||||
|
patternTxt=r'href="(?P<url>.+?)" target="_blank" alt="(?P<title>.+?)" title=".+?">'
|
||||||
|
videoList=self.get_EpisodesList_re(htmlTxt=htmlTxt,patternTxt=patternTxt)
|
||||||
|
fromId='央视'
|
||||||
|
except:
|
||||||
|
pass
|
||||||
|
if len(videoList) == 0:
|
||||||
|
return {}
|
||||||
|
vod = {
|
||||||
|
"vod_id":array[0],
|
||||||
|
"vod_name":title,
|
||||||
|
"vod_pic":logo,
|
||||||
|
"type_name":tid,
|
||||||
|
"vod_year":vod_year,
|
||||||
|
"vod_area":"",
|
||||||
|
"vod_remarks":'',
|
||||||
|
"vod_actor":actors,
|
||||||
|
"vod_director":'',
|
||||||
|
"vod_content":brief
|
||||||
|
}
|
||||||
|
vod['vod_play_from'] = fromId
|
||||||
|
vod['vod_play_url'] = "#".join(videoList)
|
||||||
|
result = {
|
||||||
|
'list':[
|
||||||
|
vod
|
||||||
|
]
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
def get_lineList(self,Txt,mark,after):
|
||||||
|
circuit=[]
|
||||||
|
origin=Txt.find(mark)
|
||||||
|
while origin>8:
|
||||||
|
end=Txt.find(after,origin)
|
||||||
|
circuit.append(Txt[origin:end])
|
||||||
|
origin=Txt.find(mark,end)
|
||||||
|
return circuit
|
||||||
|
def get_RegexGetTextLine(self,Text,RegexText,Index):
|
||||||
|
returnTxt=[]
|
||||||
|
pattern = re.compile(RegexText, re.M|re.S)
|
||||||
|
ListRe=pattern.findall(Text)
|
||||||
|
if len(ListRe)<1:
|
||||||
|
return returnTxt
|
||||||
|
for value in ListRe:
|
||||||
|
returnTxt.append(value)
|
||||||
|
return returnTxt
|
||||||
|
def searchContent(self,key,quick):
|
||||||
|
return self.searchContentPage(key, quick, '1')
|
||||||
|
def searchContentPage(self, key, quick, page):
|
||||||
|
key=urllib.parse.quote(key)
|
||||||
|
Url='https://search.cctv.com/ifsearch.php?page=1&qtext={0}&sort=relevance&pageSize=20&type=video&vtime=-1&datepid=1&channel=&pageflag=0&qtext_str={0}'.format(key)
|
||||||
|
htmlTxt=self.webReadFile(urlStr=Url,header=self.header)
|
||||||
|
videos=self.get_list_search(html=htmlTxt,tid='搜索')
|
||||||
|
result = {
|
||||||
|
'list':videos
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
def playerContent(self,flag,id,vipFlags):
|
||||||
|
result = {}
|
||||||
|
url=''
|
||||||
|
parse=0
|
||||||
|
headers = {
|
||||||
|
'User-Agent':'Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1'
|
||||||
|
}
|
||||||
|
if flag=='CCTV':
|
||||||
|
url=self.get_m3u8(urlTxt=id)
|
||||||
|
else:
|
||||||
|
try:
|
||||||
|
html=self.webReadFile(urlStr=id,header=self.header)
|
||||||
|
guid=self.get_RegexGetText(Text=html,RegexText=r'var\sguid\s*=\s*"(.+?)";',Index=1)
|
||||||
|
url=self.get_m3u8(urlTxt=guid)
|
||||||
|
except :
|
||||||
|
url=id
|
||||||
|
parse=1
|
||||||
|
if url.find('https:')<0:
|
||||||
|
url=id
|
||||||
|
parse=1
|
||||||
|
result["parse"] = parse#1=嗅探,0=播放
|
||||||
|
result["playUrl"] = ''
|
||||||
|
result["url"] = url
|
||||||
|
result["header"] =headers
|
||||||
|
return result
|
||||||
|
config = {
|
||||||
|
"player": {},
|
||||||
|
"filter": {
|
||||||
|
"电视剧":[
|
||||||
|
{"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"谍战","v":"谍战"},{"n":"悬疑","v":"悬疑"},{"n":"刑侦","v":"刑侦"},{"n":"历史","v":"历史"},{"n":"古装","v":"古装"},{"n":"武侠","v":"武侠"},{"n":"军旅","v":"军旅"},{"n":"战争","v":"战争"},{"n":"喜剧","v":"喜剧"},{"n":"青春","v":"青春"},{"n":"言情","v":"言情"},{"n":"偶像","v":"偶像"},{"n":"家庭","v":"家庭"},{"n":"年代","v":"年代"},{"n":"革命","v":"革命"},{"n":"农村","v":"农村"},{"n":"都市","v":"都市"},{"n":"其他","v":"其他"}]},
|
||||||
|
{"key":"datadq-area","name":"地区","value":[{"n":"全部","v":""},{"n":"中国大陆","v":"中国大陆"},{"n":"中国香港","v":"香港"},{"n":"美国","v":"美国"},{"n":"欧洲","v":"欧洲"},{"n":"泰国","v":"泰国"}]},
|
||||||
|
{"key":"datanf-year","name":"年份","value":[{"n":"全部","v":""},{"n":"2023","v":"2023"},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2018","v":"2018"},{"n":"2017","v":"2017"},{"n":"2016","v":"2016"},{"n":"2015","v":"2015"},{"n":"2014","v":"2014"},{"n":"2013","v":"2013"},{"n":"2012","v":"2012"},{"n":"2011","v":"2011"},{"n":"2010","v":"2010"},{"n":"2009","v":"2009"},{"n":"2008","v":"2008"},{"n":"2007","v":"2007"},{"n":"2006","v":"2006"},{"n":"2005","v":"2005"},{"n":"2004","v":"2004"},{"n":"2003","v":"2003"},{"n":"2002","v":"2002"},{"n":"2001","v":"2001"},{"n":"2000","v":"2000"},{"n":"1999","v":"1999"},{"n":"1998","v":"1998"},{"n":"1997","v":"1997"}]},
|
||||||
|
{"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]}
|
||||||
|
],
|
||||||
|
"动画片":[
|
||||||
|
{"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"亲子","v":"亲子"},{"n":"搞笑","v":"搞笑"},{"n":"冒险","v":"冒险"},{"n":"动作","v":"动作"},{"n":"宠物","v":"宠物"},{"n":"体育","v":"体育"},{"n":"益智","v":"益智"},{"n":"历史","v":"历史"},{"n":"教育","v":"教育"},{"n":"校园","v":"校园"},{"n":"言情","v":"言情"},{"n":"武侠","v":"武侠"},{"n":"经典","v":"经典"},{"n":"未来","v":"未来"},{"n":"古代","v":"古代"},{"n":"神话","v":"神话"},{"n":"真人","v":"真人"},{"n":"励志","v":"励志"},{"n":"热血","v":"热血"},{"n":"奇幻","v":"奇幻"},{"n":"童话","v":"童话"},{"n":"剧情","v":"剧情"},{"n":"夺宝","v":"夺宝"},{"n":"其他","v":"其他"}]},
|
||||||
|
{"key":"datadq-area","name":"地区","value":[{"n":"全部","v":""},{"n":"中国大陆","v":"中国大陆"},{"n":"美国","v":"美国"},{"n":"欧洲","v":"欧洲"}]},
|
||||||
|
{"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]}
|
||||||
|
],
|
||||||
|
"纪录片":[
|
||||||
|
{"key":"datapd-channel","name":"频道","value":[{"n":"全部","v":""},{"n":"CCTV{1 综合","v":"CCTV{1 综合"},{"n":"CCTV{2 财经","v":"CCTV{2 财经"},{"n":"CCTV{3 综艺","v":"CCTV{3 综艺"},{"n":"CCTV{4 中文国际","v":"CCTV{4 中文国际"},{"n":"CCTV{5 体育","v":"CCTV{5 体育"},{"n":"CCTV{6 电影","v":"CCTV{6 电影"},{"n":"CCTV{7 国防军事","v":"CCTV{7 国防军事"},{"n":"CCTV{8 电视剧","v":"CCTV{8 电视剧"},{"n":"CCTV{9 纪录","v":"CCTV{9 纪录"},{"n":"CCTV{10 科教","v":"CCTV{10 科教"},{"n":"CCTV{11 戏曲","v":"CCTV{11 戏曲"},{"n":"CCTV{12 社会与法","v":"CCTV{12 社会与法"},{"n":"CCTV{13 新闻","v":"CCTV{13 新闻"},{"n":"CCTV{14 少儿","v":"CCTV{14 少儿"},{"n":"CCTV{15 音乐","v":"CCTV{15 音乐"},{"n":"CCTV{17 农业农村","v":"CCTV{17 农业农村"}]},
|
||||||
|
{"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"人文历史","v":"人文历史"},{"n":"人物","v":"人物"},{"n":"军事","v":"军事"},{"n":"探索","v":"探索"},{"n":"社会","v":"社会"},{"n":"时政","v":"时政"},{"n":"经济","v":"经济"},{"n":"科技","v":"科技"}]},
|
||||||
|
{"key":"datanf-year","name":"年份","value":[{"n":"全部","v":""},{"n":"2023","v":"2023"},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2018","v":"2018"},{"n":"2017","v":"2017"},{"n":"2016","v":"2016"},{"n":"2015","v":"2015"},{"n":"2014","v":"2014"},{"n":"2013","v":"2013"},{"n":"2012","v":"2012"},{"n":"2011","v":"2011"},{"n":"2010","v":"2010"},{"n":"2009","v":"2009"},{"n":"2008","v":"2008"}]},
|
||||||
|
{"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]}
|
||||||
|
],
|
||||||
|
"特别节目":[
|
||||||
|
{"key":"datapd-channel","name":"频道","value":[{"n":"全部","v":""},{"n":"CCTV{1 综合","v":"CCTV{1 综合"},{"n":"CCTV{2 财经","v":"CCTV{2 财经"},{"n":"CCTV{3 综艺","v":"CCTV{3 综艺"},{"n":"CCTV{4 中文国际","v":"CCTV{4 中文国际"},{"n":"CCTV{5 体育","v":"CCTV{5 体育"},{"n":"CCTV{6 电影","v":"CCTV{6 电影"},{"n":"CCTV{7 国防军事","v":"CCTV{7 国防军事"},{"n":"CCTV{8 电视剧","v":"CCTV{8 电视剧"},{"n":"CCTV{9 纪录","v":"CCTV{9 纪录"},{"n":"CCTV{10 科教","v":"CCTV{10 科教"},{"n":"CCTV{11 戏曲","v":"CCTV{11 戏曲"},{"n":"CCTV{12 社会与法","v":"CCTV{12 社会与法"},{"n":"CCTV{13 新闻","v":"CCTV{13 新闻"},{"n":"CCTV{14 少儿","v":"CCTV{14 少儿"},{"n":"CCTV{15 音乐","v":"CCTV{15 音乐"},{"n":"CCTV{17 农业农村","v":"CCTV{17 农业农村"}]},
|
||||||
|
{"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"全部","v":"全部"},{"n":"新闻","v":"新闻"},{"n":"经济","v":"经济"},{"n":"综艺","v":"综艺"},{"n":"体育","v":"体育"},{"n":"军事","v":"军事"},{"n":"影视","v":"影视"},{"n":"科教","v":"科教"},{"n":"戏曲","v":"戏曲"},{"n":"青少","v":"青少"},{"n":"音乐","v":"音乐"},{"n":"社会","v":"社会"},{"n":"公益","v":"公益"},{"n":"其他","v":"其他"}]},
|
||||||
|
{"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]}
|
||||||
|
],
|
||||||
|
"节目大全":[{"key":"cid","name":"频道","value":[{"n":"全部","v":""},{"n":"CCTV-1综合","v":"EPGC1386744804340101"},{"n":"CCTV-2财经","v":"EPGC1386744804340102"},{"n":"CCTV-3综艺","v":"EPGC1386744804340103"},{"n":"CCTV-4中文国际","v":"EPGC1386744804340104"},{"n":"CCTV-5体育","v":"EPGC1386744804340107"},{"n":"CCTV-6电影","v":"EPGC1386744804340108"},{"n":"CCTV-7国防军事","v":"EPGC1386744804340109"},{"n":"CCTV-8电视剧","v":"EPGC1386744804340110"},{"n":"CCTV-9纪录","v":"EPGC1386744804340112"},{"n":"CCTV-10科教","v":"EPGC1386744804340113"},{"n":"CCTV-11戏曲","v":"EPGC1386744804340114"},{"n":"CCTV-12社会与法","v":"EPGC1386744804340115"},{"n":"CCTV-13新闻","v":"EPGC1386744804340116"},{"n":"CCTV-14少儿","v":"EPGC1386744804340117"},{"n":"CCTV-15音乐","v":"EPGC1386744804340118"},{"n":"CCTV-16奥林匹克","v":"EPGC1634630207058998"},{"n":"CCTV-17农业农村","v":"EPGC1563932742616872"},{"n":"CCTV-5+体育赛事","v":"EPGC1468294755566101"}]},{"key":"fc","name":"分类","value":[{"n":"全部","v":""},{"n":"新闻","v":"新闻"},{"n":"体育","v":"体育"},{"n":"综艺","v":"综艺"},{"n":"健康","v":"健康"},{"n":"生活","v":"生活"},{"n":"科教","v":"科教"},{"n":"经济","v":"经济"},{"n":"农业","v":"农业"},{"n":"法治","v":"法治"},{"n":"军事","v":"军事"},{"n":"少儿","v":"少儿"},{"n":"动画","v":"动画"},{"n":"纪实","v":"纪实"},{"n":"戏曲","v":"戏曲"},{"n":"音乐","v":"音乐"},{"n":"影视","v":"影视"}]},{"key":"fl","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"B","v":"B"},{"n":"C","v":"C"},{"n":"D","v":"D"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"}]},{"key":"year","name":"年份","value":[{"n":"全部","v":""},{"n":"2023","v":"2023"},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2018","v":"2018"},{"n":"2017","v":"2017"},{"n":"2016","v":"2016"},{"n":"2015","v":"2015"},{"n":"2014","v":"2014"},{"n":"2013","v":"2013"},{"n":"2012","v":"2012"},{"n":"2011","v":"2011"},{"n":"2010","v":"2010"},{"n":"2009","v":"2009"},{"n":"2008","v":"2008"},{"n":"2007","v":"2007"},{"n":"2006","v":"2006"},{"n":"2005","v":"2005"},{"n":"2004","v":"2004"},{"n":"2003","v":"2003"},{"n":"2002","v":"2002"},{"n":"2001","v":"2001"},{"n":"2000","v":"2000"}]},{"key":"month","name":"月份","value":[{"n":"全部","v":""},{"n":"12","v":"12"},{"n":"11","v":"11"},{"n":"10","v":"10"},{"n":"09","v":"09"},{"n":"08","v":"08"},{"n":"07","v":"07"},{"n":"06","v":"06"},{"n":"05","v":"05"},{"n":"04","v":"04"},{"n":"03","v":"03"},{"n":"02","v":"02"},{"n":"01","v":"01"}]}]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
header = {
|
||||||
|
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.54 Safari/537.36",
|
||||||
|
"Host": "tv.cctv.com",
|
||||||
|
"Referer": "https://tv.cctv.com/"
|
||||||
|
}
|
||||||
|
|
||||||
|
def localProxy(self,param):
|
||||||
|
return [200, "video/MP2T", ""]
|
||||||
|
#-----------------------------------------------自定义函数-----------------------------------------------
|
||||||
|
#访问网页
|
||||||
|
def webReadFile(self,urlStr,header):
|
||||||
|
html=''
|
||||||
|
req=urllib.request.Request(url=urlStr)#,headers=header
|
||||||
|
with urllib.request.urlopen(req) as response:
|
||||||
|
html = response.read().decode('utf-8')
|
||||||
|
return html
|
||||||
|
#判断网络地址是否存在
|
||||||
|
def TestWebPage(self,urlStr,header):
|
||||||
|
html=''
|
||||||
|
req=urllib.request.Request(url=urlStr,method='HEAD')#,headers=header
|
||||||
|
with urllib.request.urlopen(req) as response:
|
||||||
|
html = response.getcode ()
|
||||||
|
return html
|
||||||
|
#正则取文本
|
||||||
|
def get_RegexGetText(self,Text,RegexText,Index):
|
||||||
|
returnTxt=""
|
||||||
|
Regex=re.search(RegexText, Text, re.M|re.S)
|
||||||
|
if Regex is None:
|
||||||
|
returnTxt=""
|
||||||
|
else:
|
||||||
|
returnTxt=Regex.group(Index)
|
||||||
|
return returnTxt
|
||||||
|
#取集数
|
||||||
|
def get_EpisodesList(self,jsonList):
|
||||||
|
videos=[]
|
||||||
|
for vod in jsonList:
|
||||||
|
url = vod['guid']
|
||||||
|
title =vod['title']
|
||||||
|
if len(url) == 0:
|
||||||
|
continue
|
||||||
|
videos.append(title+"$"+url)
|
||||||
|
return videos
|
||||||
|
#取集数
|
||||||
|
def get_EpisodesList_re(self,htmlTxt,patternTxt):
|
||||||
|
ListRe=re.finditer(patternTxt, htmlTxt, re.M|re.S)
|
||||||
|
videos=[]
|
||||||
|
for vod in ListRe:
|
||||||
|
url = vod.group('url')
|
||||||
|
title =vod.group('title')
|
||||||
|
if len(url) == 0:
|
||||||
|
continue
|
||||||
|
videos.append(title+"$"+url)
|
||||||
|
return videos
|
||||||
|
#取剧集区
|
||||||
|
def get_lineList(self,Txt,mark,after):
|
||||||
|
circuit=[]
|
||||||
|
origin=Txt.find(mark)
|
||||||
|
while origin>8:
|
||||||
|
end=Txt.find(after,origin)
|
||||||
|
circuit.append(Txt[origin:end])
|
||||||
|
origin=Txt.find(mark,end)
|
||||||
|
return circuit
|
||||||
|
#正则取文本,返回数组
|
||||||
|
def get_RegexGetTextLine(self,Text,RegexText,Index):
|
||||||
|
returnTxt=[]
|
||||||
|
pattern = re.compile(RegexText, re.M|re.S)
|
||||||
|
ListRe=pattern.findall(Text)
|
||||||
|
if len(ListRe)<1:
|
||||||
|
return returnTxt
|
||||||
|
for value in ListRe:
|
||||||
|
returnTxt.append(value)
|
||||||
|
return returnTxt
|
||||||
|
#删除html标签
|
||||||
|
def removeHtml(self,txt):
|
||||||
|
soup = re.compile(r'<[^>]+>',re.S)
|
||||||
|
txt =soup.sub('', txt)
|
||||||
|
return txt.replace(" "," ")
|
||||||
|
#取m3u8
|
||||||
|
def get_m3u8(self,urlTxt):
|
||||||
|
url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(urlTxt)
|
||||||
|
html=self.webReadFile(urlStr=url,header=self.header)
|
||||||
|
jo =json.loads(html)
|
||||||
|
link = jo['hls_url'].strip()
|
||||||
|
html = self.webReadFile(urlStr=link,header=self.header)
|
||||||
|
content = html.strip()
|
||||||
|
arr = content.split('\n')
|
||||||
|
urlPrefix = self.get_RegexGetText(Text=link,RegexText='(http[s]?://[a-zA-z0-9.]+)/',Index=1)
|
||||||
|
subUrl = arr[-1].split('/')
|
||||||
|
subUrl[3] = '1200'
|
||||||
|
subUrl[-1] = '1200.m3u8'
|
||||||
|
hdUrl = urlPrefix + '/'.join(subUrl)
|
||||||
|
|
||||||
|
url = urlPrefix + arr[-1]
|
||||||
|
|
||||||
|
hdRsp = self.TestWebPage(urlStr=hdUrl,header=self.header)
|
||||||
|
if hdRsp == 200:
|
||||||
|
url = hdUrl
|
||||||
|
else:
|
||||||
|
url=''
|
||||||
|
return url
|
||||||
|
#搜索
|
||||||
|
def get_list_search(self,html,tid):
|
||||||
|
jRoot = json.loads(html)
|
||||||
|
jsonList=jRoot['list']
|
||||||
|
videos=[]
|
||||||
|
for vod in jsonList:
|
||||||
|
url = vod['urllink']
|
||||||
|
title =self.removeHtml(txt=vod['title'])
|
||||||
|
img=vod['imglink']
|
||||||
|
id=vod['id']
|
||||||
|
brief=vod['channel']
|
||||||
|
year=vod['uploadtime']
|
||||||
|
if len(url) == 0:
|
||||||
|
continue
|
||||||
|
guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,'',brief)
|
||||||
|
videos.append({
|
||||||
|
"vod_id":guid,
|
||||||
|
"vod_name":title,
|
||||||
|
"vod_pic":img,
|
||||||
|
"vod_remarks":year
|
||||||
|
})
|
||||||
|
return videos
|
||||||
|
return videos
|
||||||
|
def get_list1(self,html,tid):
|
||||||
|
jRoot = json.loads(html)
|
||||||
|
videos = []
|
||||||
|
data=jRoot['response']
|
||||||
|
if data is None:
|
||||||
|
return []
|
||||||
|
jsonList=data['docs']
|
||||||
|
for vod in jsonList:
|
||||||
|
id = vod['lastVIDE']['videoSharedCode']
|
||||||
|
title =vod['column_name']
|
||||||
|
url=vod['column_website']
|
||||||
|
img=vod['column_logo']
|
||||||
|
year=vod['column_playdate']
|
||||||
|
brief=vod['column_brief']
|
||||||
|
actors=''
|
||||||
|
if len(url) == 0:
|
||||||
|
continue
|
||||||
|
guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief)
|
||||||
|
#print(vod_id)
|
||||||
|
videos.append({
|
||||||
|
"vod_id":guid,
|
||||||
|
"vod_name":title,
|
||||||
|
"vod_pic":img,
|
||||||
|
"vod_remarks":''
|
||||||
|
})
|
||||||
|
#print(videos)
|
||||||
|
return videos
|
||||||
|
#分类取结果
|
||||||
|
def get_list(self,html,tid):
|
||||||
|
jRoot = json.loads(html)
|
||||||
|
videos = []
|
||||||
|
data=jRoot['data']
|
||||||
|
if data is None:
|
||||||
|
return []
|
||||||
|
jsonList=data['list']
|
||||||
|
for vod in jsonList:
|
||||||
|
url = vod['url']
|
||||||
|
title =vod['title']
|
||||||
|
img=vod['image']
|
||||||
|
id=vod['id']
|
||||||
|
try:
|
||||||
|
brief=vod['brief']
|
||||||
|
except:
|
||||||
|
brief=''
|
||||||
|
try:
|
||||||
|
year=vod['year']
|
||||||
|
except:
|
||||||
|
year=''
|
||||||
|
try:
|
||||||
|
actors=vod['actors']
|
||||||
|
except:
|
||||||
|
actors=''
|
||||||
|
if len(url) == 0:
|
||||||
|
continue
|
||||||
|
guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief)
|
||||||
|
#print(vod_id)
|
||||||
|
videos.append({
|
||||||
|
"vod_id":guid,
|
||||||
|
"vod_name":title,
|
||||||
|
"vod_pic":img,
|
||||||
|
"vod_remarks":''
|
||||||
|
})
|
||||||
|
return videos
|
||||||
+242
@@ -0,0 +1,242 @@
|
|||||||
|
#coding=utf-8
|
||||||
|
#!/usr/bin/python
|
||||||
|
import sys
|
||||||
|
sys.path.append('..')
|
||||||
|
from base.spider import Spider
|
||||||
|
import json
|
||||||
|
import time
|
||||||
|
import base64
|
||||||
|
import requests
|
||||||
|
|
||||||
|
class Spider(Spider):
|
||||||
|
def getName(self):
|
||||||
|
return "央视综艺"
|
||||||
|
|
||||||
|
def init(self, extend=""):
|
||||||
|
print("============{0}============".format(extend))
|
||||||
|
pass
|
||||||
|
|
||||||
|
def isVideoFormat(self, url):
|
||||||
|
pass
|
||||||
|
|
||||||
|
def manualVideoCheck(self):
|
||||||
|
pass
|
||||||
|
|
||||||
|
def homeContent(self, filter):
|
||||||
|
result = {}
|
||||||
|
cateManual = {
|
||||||
|
"中华情": "TOPC1451541564922207",
|
||||||
|
"回声嘹亮": "TOPC1451535575561597",
|
||||||
|
"你好生活第三季": "TOPC1627961377879898",
|
||||||
|
"我的艺术清单": "TOPC1582272259917160",
|
||||||
|
"黄金100秒": "TOPC1451468496522494",
|
||||||
|
"非常6+1": "TOPC1451467940101208",
|
||||||
|
"向幸福出发": "TOPC1451984638791216",
|
||||||
|
"幸福账单": "TOPC1451984801613379",
|
||||||
|
"中国文艺报道": "TOPC1601348042760302",
|
||||||
|
"舞蹈世界": "TOPC1451547605511387",
|
||||||
|
"艺览天下": "TOPC1451984851125433",
|
||||||
|
"天天把歌唱": "TOPC1451535663610626",
|
||||||
|
"金牌喜剧班": "TOPC1611826337610628",
|
||||||
|
"环球综艺秀": "TOPC1571300682556971",
|
||||||
|
"挑战不可能第五季": "TOPC1579169060379297",
|
||||||
|
"我们有一套": "TOPC1451527089955940",
|
||||||
|
"为了你": "TOPC1451527001597710",
|
||||||
|
"朗读者第一季": "TOPC1487120479377477",
|
||||||
|
"挑战不可能第二季": "TOPC1474277421637816",
|
||||||
|
"精彩一刻": "TOPC1451464786232149",
|
||||||
|
"挑战不可能之加油中国": "TOPC1547519813971570",
|
||||||
|
"挑战不可能第一季": "TOPC1452063816677656",
|
||||||
|
"机智过人第三季": "TOPC1564019920570762",
|
||||||
|
"经典咏流传第二季": "TOPC1547521714115947",
|
||||||
|
"挑战不可能第三季": "TOPC1509500865106312",
|
||||||
|
"经典咏流传第一季": "TOPC1513676755770201",
|
||||||
|
"欢乐中国人第二季": "TOPC1516784350726581",
|
||||||
|
"故事里的中国第一季": "TOPC1569729252342702",
|
||||||
|
"你好生活第二季": "TOPC1604397385056621",
|
||||||
|
"喜上加喜": "TOPC1590026042145705",
|
||||||
|
"走在回家的路上": "TOPC1577697653272281",
|
||||||
|
"综艺盛典": "TOPC1451985071887935",
|
||||||
|
"艺术人生": "TOPC1451984891490556",
|
||||||
|
"全家好拍档": "TOPC1474275463547690",
|
||||||
|
"大魔术师": "TOPC1451984047073332",
|
||||||
|
"欢乐一家亲": "TOPC1451984214170587",
|
||||||
|
"开心辞典": "TOPC1451984378754815",
|
||||||
|
"综艺星天地": "TOPC1451985188986150",
|
||||||
|
"激情广场": "TOPC1451984341218765",
|
||||||
|
"笑星大联盟": "TOPC1451984731428297",
|
||||||
|
"天天乐": "TOPC1451984447718918",
|
||||||
|
"欢乐英雄": "TOPC1451984242834620",
|
||||||
|
"欢乐中国行": "TOPC1451984301286720",
|
||||||
|
"我爱满堂彩": "TOPC1451538709371329",
|
||||||
|
"综艺头条": "TOPC1569226855085860",
|
||||||
|
"中华情": "TOPC1451541564922207",
|
||||||
|
"魔法奇迹": "TOPC1451542029126607"
|
||||||
|
}
|
||||||
|
classes = []
|
||||||
|
for k in cateManual:
|
||||||
|
classes.append({
|
||||||
|
'type_name': k,
|
||||||
|
'type_id': cateManual[k]
|
||||||
|
})
|
||||||
|
result['class'] = classes
|
||||||
|
if filter:
|
||||||
|
result['filters'] = self.config['filter']
|
||||||
|
return result
|
||||||
|
|
||||||
|
def homeVideoContent(self):
|
||||||
|
result = {
|
||||||
|
'list': []
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
|
||||||
|
def categoryContent(self, tid, pg, filter, extend):
|
||||||
|
result = {}
|
||||||
|
extend['id'] = tid
|
||||||
|
extend['p'] = pg
|
||||||
|
filterParams = ["id", "p", "d"]
|
||||||
|
params = ["", "", ""]
|
||||||
|
for idx in range(len(filterParams)):
|
||||||
|
fp = filterParams[idx]
|
||||||
|
if fp in extend.keys():
|
||||||
|
params[idx] = '{0}={1}'.format(filterParams[idx], extend[fp])
|
||||||
|
suffix = '&'.join(params)
|
||||||
|
url = 'https://api.cntv.cn/NewVideo/getVideoListByColumn?{0}&n=20&sort=desc&mode=0&serviceId=tvcctv&t=json'.format(suffix)
|
||||||
|
if not tid.startswith('TOPC'):
|
||||||
|
url = 'https://api.cntv.cn/NewVideo/getVideoListByAlbumIdNew?{0}&n=20&sort=desc&mode=0&serviceId=tvcctv&t=json'.format(suffix)
|
||||||
|
rsp = self.fetch(url, headers=self.header)
|
||||||
|
jo = json.loads(rsp.text)
|
||||||
|
vodList = jo['data']['list']
|
||||||
|
videos = []
|
||||||
|
for vod in vodList:
|
||||||
|
guid = vod['guid']
|
||||||
|
title = vod['title']
|
||||||
|
img = vod['image']
|
||||||
|
brief = vod['brief']
|
||||||
|
videos.append({
|
||||||
|
"vod_id": guid + "###" + img,
|
||||||
|
"vod_name": title,
|
||||||
|
"vod_pic": img,
|
||||||
|
"vod_remarks": ''
|
||||||
|
})
|
||||||
|
result['list'] = videos
|
||||||
|
result['page'] = pg
|
||||||
|
result['pagecount'] = 9999
|
||||||
|
result['limit'] = 90
|
||||||
|
result['total'] = 999999
|
||||||
|
return result
|
||||||
|
|
||||||
|
def detailContent(self, array):
|
||||||
|
aid = array[0].split('###')
|
||||||
|
tid = aid[0]
|
||||||
|
url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(tid)
|
||||||
|
|
||||||
|
rsp = self.fetch(url, headers=self.header)
|
||||||
|
jo = json.loads(rsp.text)
|
||||||
|
title = jo['title'].strip()
|
||||||
|
link = jo['hls_url'].strip()
|
||||||
|
vod = {
|
||||||
|
"vod_id": tid,
|
||||||
|
"vod_name": title,
|
||||||
|
"vod_pic": aid[1],
|
||||||
|
"type_name": '',
|
||||||
|
"vod_year": "",
|
||||||
|
"vod_area": "",
|
||||||
|
"vod_remarks": "",
|
||||||
|
"vod_actor": "",
|
||||||
|
"vod_director": "",
|
||||||
|
"vod_content": ""
|
||||||
|
}
|
||||||
|
vod['vod_play_from'] = 'CCTV'
|
||||||
|
vod['vod_play_url'] = title + "$" + link
|
||||||
|
|
||||||
|
result = {
|
||||||
|
'list': [vod]
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
|
||||||
|
def searchContent(self, key, quick):
|
||||||
|
result = {
|
||||||
|
'list': []
|
||||||
|
}
|
||||||
|
return result
|
||||||
|
|
||||||
|
def playerContent(self, flag, id, vipFlags):
|
||||||
|
result = {}
|
||||||
|
# 先尝试获取原始m3u8文件
|
||||||
|
rsp = self.fetch(id, headers=self.header)
|
||||||
|
content = rsp.text.strip()
|
||||||
|
|
||||||
|
if not content:
|
||||||
|
# 如果获取失败，直接返回原始链接
|
||||||
|
result["parse"] = 0
|
||||||
|
result["playUrl"] = ''
|
||||||
|
result["url"] = id
|
||||||
|
result["header"] = self.header
|
||||||
|
return result
|
||||||
|
|
||||||
|
arr = content.split('\n')
|
||||||
|
urlPrefix = self.regStr(id, '(http[s]?://[a-zA-z0-9.]+)/')
|
||||||
|
|
||||||
|
# 尝试获取高清链接
|
||||||
|
resolutions = ['2000', '1200', '800'] # 从高到低尝试
|
||||||
|
final_url = id # 默认使用原始链接
|
||||||
|
|
||||||
|
for res in resolutions:
|
||||||
|
try:
|
||||||
|
subUrl = arr[-1].split('/')
|
||||||
|
subUrl[3] = res
|
||||||
|
subUrl[-1] = f'{res}.m3u8'
|
||||||
|
hdUrl = urlPrefix + '/'.join(subUrl)
|
||||||
|
|
||||||
|
# 检查高清链接是否有效
|
||||||
|
hdRsp = requests.head(hdUrl, headers=self.header, timeout=5)
|
||||||
|
if hdRsp.status_code == 200:
|
||||||
|
final_url = hdUrl
|
||||||
|
break
|
||||||
|
except:
|
||||||
|
continue
|
||||||
|
|
||||||
|
result["parse"] = 0
|
||||||
|
result["playUrl"] = ''
|
||||||
|
result["url"] = final_url
|
||||||
|
result["header"] = self.header
|
||||||
|
return result
|
||||||
|
|
||||||
|
config = {
|
||||||
|
"player": {},
|
||||||
|
"filter": {
|
||||||
|
"TOPC1451557970755294": [
|
||||||
|
{
|
||||||
|
"key": "d",
|
||||||
|
"name": "年份",
|
||||||
|
"value": [
|
||||||
|
{"n": "全部", "v": ""},
|
||||||
|
{"n": "2023", "v": "2023"},
|
||||||
|
{"n": "2022", "v": "2022"},
|
||||||
|
{"n": "2021", "v": "2021"},
|
||||||
|
{"n": "2020", "v": "2020"},
|
||||||
|
{"n": "2019", "v": "2019"},
|
||||||
|
{"n": "2018", "v": "2018"},
|
||||||
|
{"n": "2017", "v": "2017"},
|
||||||
|
{"n": "2016", "v": "2016"},
|
||||||
|
{"n": "2015", "v": "2015"},
|
||||||
|
{"n": "2014", "v": "2014"},
|
||||||
|
{"n": "2013", "v": "2013"},
|
||||||
|
{"n": "2012", "v": "2012"},
|
||||||
|
{"n": "2011", "v": "2011"},
|
||||||
|
{"n": "2010", "v": "2010"},
|
||||||
|
{"n": "2009", "v": "2009"}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
header = {
|
||||||
|
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.54 Safari/537.36",
|
||||||
|
"Referer": "https://www.cctv.com/",
|
||||||
|
"Origin": "https://www.cctv.com"
|
||||||
|
}
|
||||||
|
|
||||||
|
def localProxy(self, param):
|
||||||
|
return [200, "video/MP2T", None, ""]
|
||||||
+350
@@ -0,0 +1,350 @@
|
|||||||
|
# -*- coding: utf-8 -*-
|
||||||
|
# 本资源来源于互联网公开渠道，仅可用于个人学习爬虫技术。
|
||||||
|
# 严禁将其用于任何商业用途，下载后请于 24 小时内删除，搜索结果均来自源站，本人不承担任何责任。
|
||||||
|
#junyouyun
|
||||||
|
|
||||||
|
import sys
|
||||||
|
import json
|
||||||
|
import time
|
||||||
|
import base64
|
||||||
|
import hashlib
|
||||||
|
import urllib3
|
||||||
|
import concurrent.futures
|
||||||
|
from urllib.parse import quote
|
||||||
|
from base.spider import Spider
|
||||||
|
from Crypto.PublicKey import RSA
|
||||||
|
from Crypto.Cipher import PKCS1_v1_5
|
||||||
|
|
||||||
|
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
|
||||||
|
sys.path.append('..')
|
||||||
|
|
||||||
|
class Spider(Spider):
|
||||||
|
host, userid, episode_list = '', '', []
|
||||||
|
|
||||||
|
# ---------- 加密与签名相关常量 ----------
|
||||||
|
PUB_KEY_B64 = "MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCoYt0BP77U+DM08BiI/QbSRIfxijXo85BTPqIM1Ow8BNwhLETzRIZ+dEwdWDbydG/PspgBAfRpGaYVdJYtvaC2JnoO8+Ik6qMWojfEJxSFLa0Pb0A892tun4gsxoEMjcreZ+YGyaBxAfqX0BSMfdrOgIYaZQjYrw9TRLlUT31QoQIDAQAB"
|
||||||
|
APP_SIGN_SHA1 = "09a8dc51639a31801af5f6418caebfabc695eb24"
|
||||||
|
DEVICE_ID = "2d590b9842d064a1"
|
||||||
|
|
||||||
|
# RSA 私钥（用于解密响应）
|
||||||
|
PRIV_KEY_B64 = """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"""
|
||||||
|
|
||||||
|
headers = {
|
||||||
|
'User-Agent': "okhttp/4.12.0",
|
||||||
|
'Connection': "Keep-Alive",
|
||||||
|
'Accept-Encoding': "gzip",
|
||||||
|
'Content-Type': "application/json;charset=UTF-8",
|
||||||
|
'Cache-Control': "no-cache",
|
||||||
|
'token': "",
|
||||||
|
'deviceId': DEVICE_ID,
|
||||||
|
'client': "app",
|
||||||
|
'deviceType': "Android"
|
||||||
|
}
|
||||||
|
|
||||||
|
# ---------- RSA 加密 ----------
|
||||||
|
def rsa_encrypt(self, data: str) -> str:
|
||||||
|
key = RSA.import_key(base64.b64decode(self.PUB_KEY_B64))
|
||||||
|
cipher = PKCS1_v1_5.new(key)
|
||||||
|
encrypted = cipher.encrypt(data.encode('utf-8'))
|
||||||
|
return base64.b64encode(encrypted).decode('utf-8')
|
||||||
|
|
||||||
|
# ---------- RSA 解密（支持分块） ----------
|
||||||
|
def rsa_decrypt(self, encrypted_b64: str) -> str:
|
||||||
|
key = RSA.import_key(base64.b64decode(self.PRIV_KEY_B64))
|
||||||
|
cipher = PKCS1_v1_5.new(key)
|
||||||
|
encrypted_bytes = base64.b64decode(encrypted_b64)
|
||||||
|
block_size = 256
|
||||||
|
decrypted_parts = []
|
||||||
|
for i in range(0, len(encrypted_bytes), block_size):
|
||||||
|
block = encrypted_bytes[i:i+block_size]
|
||||||
|
decrypted_parts.append(cipher.decrypt(block, None))
|
||||||
|
return b''.join(decrypted_parts).decode('utf-8')
|
||||||
|
|
||||||
|
# ---------- 构建签名参数 ----------
|
||||||
|
def build_params_string(self, episode_id="", episode_index="", vid="", player_id="", type_id="", user_id=""):
|
||||||
|
return (f"episodeId{episode_id}"
|
||||||
|
f"episodeIndex{episode_index}"
|
||||||
|
f"id{vid}"
|
||||||
|
f"playerId{player_id}"
|
||||||
|
f"source0"
|
||||||
|
f"typeId{type_id}"
|
||||||
|
f"userId{user_id}")
|
||||||
|
|
||||||
|
def generate_sign(self, timestamp: str, params_str: str, device_id: str) -> str:
|
||||||
|
raw = f"SaltLSFBTimestamp{timestamp}Params{params_str}ClientappDeviceId{device_id}"
|
||||||
|
b64 = base64.b64encode(raw.encode('utf-8')).decode('utf-8')
|
||||||
|
md5 = hashlib.md5(b64.encode('utf-8')).hexdigest().upper()
|
||||||
|
return md5
|
||||||
|
|
||||||
|
def build_encrypted_headers(self, body_json: str, params_str: str) -> dict:
|
||||||
|
timestamp = str(int(time.time()))
|
||||||
|
encrypted_key = self.rsa_encrypt(body_json)
|
||||||
|
snjm = self.rsa_encrypt("113")
|
||||||
|
appsign = self.rsa_encrypt(self.APP_SIGN_SHA1)
|
||||||
|
sign = self.generate_sign(timestamp, params_str, self.DEVICE_ID)
|
||||||
|
|
||||||
|
headers = {
|
||||||
|
"snjm": snjm,
|
||||||
|
"appsign": appsign,
|
||||||
|
"timestamp": timestamp,
|
||||||
|
"sign": sign,
|
||||||
|
"deviceId": self.DEVICE_ID,
|
||||||
|
"token": self.headers.get('token', ''),
|
||||||
|
"client": "app",
|
||||||
|
"deviceType": "Android",
|
||||||
|
"Content-Type": "application/json;charset=UTF-8",
|
||||||
|
"Cache-Control": "no-cache",
|
||||||
|
"User-Agent": "okhttp/4.12.0"
|
||||||
|
}
|
||||||
|
return headers, {"key": encrypted_key}
|
||||||
|
|
||||||
|
# ---------- 原有接口（保持不变） ----------
|
||||||
|
def init(self, extend=''):
|
||||||
|
self.headers['deviceId'] = self.DEVICE_ID
|
||||||
|
self.host = 'http://qkys.qukanwh.com'
|
||||||
|
response = self.fetch(f'{self.host}/api/v1/app/user/visitorInfo', headers=self.headers).json()
|
||||||
|
self.userid = response['data']['id']
|
||||||
|
token = response['data']['token']
|
||||||
|
self.headers['token'] = token
|
||||||
|
|
||||||
|
def homeContent(self, filter):
|
||||||
|
response = self.post(f'{self.host}/api/v1/app/screen/screenType', headers=self.headers).json()
|
||||||
|
data = response['data']
|
||||||
|
classes = []
|
||||||
|
for i in data:
|
||||||
|
classes.append({'type_id': i['id'], 'type_name': i['name']})
|
||||||
|
return {'class': classes}
|
||||||
|
|
||||||
|
def homeVideoContent(self):
|
||||||
|
response = self.post(f'{self.host}/api/v1/app/recommend/recommendList', headers=self.headers).json()
|
||||||
|
data = response['data']
|
||||||
|
videos = []
|
||||||
|
with concurrent.futures.ThreadPoolExecutor() as executor:
|
||||||
|
future_to_id = {
|
||||||
|
executor.submit(
|
||||||
|
self.post,
|
||||||
|
f'{self.host}/api/v1/app/recommend/recommendSubList',
|
||||||
|
data=json.dumps({
|
||||||
|
"condition": item['id'],
|
||||||
|
"pageNum": 1,
|
||||||
|
"pageSize": 6
|
||||||
|
}),
|
||||||
|
headers=self.headers
|
||||||
|
): item['id'] for item in data
|
||||||
|
}
|
||||||
|
for future in concurrent.futures.as_completed(future_to_id):
|
||||||
|
try:
|
||||||
|
response = future.result().json()
|
||||||
|
for video in response['data']['records']:
|
||||||
|
videos.append({
|
||||||
|
"vod_id": video['id'],
|
||||||
|
"vod_name": video['name'],
|
||||||
|
"vod_pic": video['cover']
|
||||||
|
})
|
||||||
|
except Exception as e:
|
||||||
|
print(f"Request failed for item {future_to_id[future]}: {str(e)}")
|
||||||
|
return {'list': videos}
|
||||||
|
|
||||||
|
def categoryContent(self, tid, pg, filter, extend):
|
||||||
|
payload = {
|
||||||
|
"condition": {
|
||||||
|
"classify": "",
|
||||||
|
"region": "",
|
||||||
|
"sreecnTypeEnum": "NEWEST",
|
||||||
|
"typeId": tid,
|
||||||
|
"year": ""
|
||||||
|
},
|
||||||
|
"pageNum": pg,
|
||||||
|
"pageSize": 40
|
||||||
|
}
|
||||||
|
response = self.post(f'{self.host}/api/v1/app/screen/screenMovie', data=json.dumps(payload), headers=self.headers).json()
|
||||||
|
videos = []
|
||||||
|
for i in response['data']['records']:
|
||||||
|
videos.append({
|
||||||
|
"vod_id": i['id'],
|
||||||
|
"vod_name": i['name'],
|
||||||
|
"vod_pic": i['cover'],
|
||||||
|
"vod_remarks": i['area'],
|
||||||
|
"vod_year": i['year']
|
||||||
|
})
|
||||||
|
return {'list': videos, 'page': pg}
|
||||||
|
|
||||||
|
def searchContent(self, key, quick, pg='1'):
|
||||||
|
payload = {
|
||||||
|
"condition": {
|
||||||
|
"value": key
|
||||||
|
},
|
||||||
|
"pageNum": pg,
|
||||||
|
"pageSize": 40
|
||||||
|
}
|
||||||
|
response = self.post(f'{self.host}/api/v1/app/search/searchMovie', data=json.dumps(payload), headers=self.headers).json()
|
||||||
|
videos = []
|
||||||
|
for i in response['data']['records']:
|
||||||
|
videos.append({
|
||||||
|
'vod_id': i['id'],
|
||||||
|
'vod_name': i['name'],
|
||||||
|
'vod_pic': i['cover'],
|
||||||
|
'vod_remarks': i['area'],
|
||||||
|
'vod_year': i['year'],
|
||||||
|
'vod_area': i['area'],
|
||||||
|
'vod_content': i['desc']
|
||||||
|
})
|
||||||
|
return {'list': videos, 'page': pg}
|
||||||
|
|
||||||
|
# ---------- 详情页（已集成解密） ----------
|
||||||
|
def detailContent(self, ids):
|
||||||
|
type_id = "M15" # 注意：原脚本写死为 M17，可根据需要修改
|
||||||
|
vid = ids[0]
|
||||||
|
body = {
|
||||||
|
"id": vid,
|
||||||
|
"source": 0,
|
||||||
|
"typeId": type_id,
|
||||||
|
"userId": self.userid,
|
||||||
|
"episodeId": "",
|
||||||
|
"episodeIndex": "",
|
||||||
|
"playerId": ""
|
||||||
|
}
|
||||||
|
body_json = json.dumps(body, separators=(',', ':'))
|
||||||
|
params_str = self.build_params_string(
|
||||||
|
episode_id="",
|
||||||
|
episode_index="",
|
||||||
|
vid=str(vid),
|
||||||
|
player_id="",
|
||||||
|
type_id=type_id,
|
||||||
|
user_id=str(self.userid)
|
||||||
|
)
|
||||||
|
headers, payload = self.build_encrypted_headers(body_json, params_str)
|
||||||
|
|
||||||
|
# 发送加密请求
|
||||||
|
resp_raw = self.post(f'{self.host}/api/v1/app/play/movieDetails', data=json.dumps(payload), headers=headers).json()
|
||||||
|
encrypted_data = resp_raw.get('data')
|
||||||
|
if not encrypted_data:
|
||||||
|
raise Exception("响应中 data 为空")
|
||||||
|
# 解密 data 字段
|
||||||
|
decrypted_json_str = self.rsa_decrypt(encrypted_data)
|
||||||
|
data = json.loads(decrypted_json_str)
|
||||||
|
|
||||||
|
# 后续处理与原脚本相同
|
||||||
|
currentplayerid = data['playerId']
|
||||||
|
play_urls = []
|
||||||
|
play_url = []
|
||||||
|
show = []
|
||||||
|
for i in data['episodeList']:
|
||||||
|
play_url.append(f"{i['episode']}${ids[0]}@{currentplayerid}@{i['id']}@episode")
|
||||||
|
play_urls.append('#'.join(play_url))
|
||||||
|
moviePlayerList = data['moviePlayerList']
|
||||||
|
for i2 in moviePlayerList:
|
||||||
|
if i2['id'] == currentplayerid:
|
||||||
|
show.append(i2['moviePlayerName'])
|
||||||
|
for j in moviePlayerList:
|
||||||
|
playerid = j['id']
|
||||||
|
episodeTotal = j.get('episodeTotal')
|
||||||
|
if playerid == currentplayerid or episodeTotal is None:
|
||||||
|
continue
|
||||||
|
play_url = []
|
||||||
|
for k in range(1, episodeTotal + 1):
|
||||||
|
play_url.append(f"第{k}集${k}@{playerid}@{ids[0]}@virtual")
|
||||||
|
play_urls.append('#'.join(play_url))
|
||||||
|
if j['moviePlayerName'] not in show:
|
||||||
|
show.append(j['moviePlayerName'])
|
||||||
|
|
||||||
|
# 获取简介（此接口可能无需加密，保持原样）
|
||||||
|
payload_desc = {
|
||||||
|
"id": ids[0],
|
||||||
|
"typeId": type_id
|
||||||
|
}
|
||||||
|
response_desc = self.post(f'{self.host}/api/v1/app/play/movieDesc', data=json.dumps(payload_desc), headers=self.headers).json()
|
||||||
|
data2 = response_desc['data']
|
||||||
|
|
||||||
|
video = {
|
||||||
|
'vod_id': data2['id'],
|
||||||
|
'vod_name': data2['name'],
|
||||||
|
'vod_pic': data2['cover'],
|
||||||
|
'vod_content': data2['introduce'],
|
||||||
|
'vod_year': data2['year'],
|
||||||
|
'vod_area': data2['area'],
|
||||||
|
'vod_remarks': '',
|
||||||
|
'vod_score': data2['score'],
|
||||||
|
'type_name': data2['classify'],
|
||||||
|
'vod_director': data2['director'],
|
||||||
|
'vod_actor': data2['star'],
|
||||||
|
'vod_play_from': '$$$'.join(show),
|
||||||
|
'vod_play_url': '$$$'.join(play_urls)
|
||||||
|
}
|
||||||
|
return {'list': [video]}
|
||||||
|
|
||||||
|
# ---------- 播放页（已集成解密） ----------
|
||||||
|
def playerContent(self, flag, id, vipflags):
|
||||||
|
param, playerid, param2, param3 = id.split('@')
|
||||||
|
if param3 == 'virtual':
|
||||||
|
payload = {
|
||||||
|
"episodeIndex": str(int(param) - 1),
|
||||||
|
"id": int(param2),
|
||||||
|
"playerId": playerid,
|
||||||
|
"source": 0,
|
||||||
|
"typeId": "M15",
|
||||||
|
"userId": self.userid,
|
||||||
|
"episodeId": ""
|
||||||
|
}
|
||||||
|
else:
|
||||||
|
payload = {
|
||||||
|
"episodeId": param2,
|
||||||
|
"id": int(param),
|
||||||
|
"playerId": playerid,
|
||||||
|
"source": 0,
|
||||||
|
"typeId": "M15",
|
||||||
|
"userId": self.userid,
|
||||||
|
"episodeIndex": ""
|
||||||
|
}
|
||||||
|
body_json = json.dumps(payload, separators=(',', ':'))
|
||||||
|
print(body_json)
|
||||||
|
params_str = self.build_params_string(
|
||||||
|
episode_id=payload.get("episodeId", ""),
|
||||||
|
episode_index=payload.get("episodeIndex", ""),
|
||||||
|
vid=str(payload["id"]),
|
||||||
|
player_id=payload["playerId"],
|
||||||
|
type_id=payload["typeId"],
|
||||||
|
user_id=str(payload["userId"])
|
||||||
|
)
|
||||||
|
print(params_str)
|
||||||
|
headers, encrypted_payload = self.build_encrypted_headers(body_json, params_str)
|
||||||
|
print(headers)
|
||||||
|
print(encrypted_payload)
|
||||||
|
# 获取播放信息（加密响应）
|
||||||
|
resp_raw = self.post(f'{self.host}/api/v1/app/play/movieDetails', data=json.dumps(encrypted_payload), headers=headers).json()
|
||||||
|
encrypted_data = resp_raw.get('data')
|
||||||
|
if not encrypted_data:
|
||||||
|
raise Exception("响应中 data 为空")
|
||||||
|
decrypted_json_str = self.rsa_decrypt(encrypted_data)
|
||||||
|
data = json.loads(decrypted_json_str)
|
||||||
|
print(data)
|
||||||
|
parse_url = data['url']
|
||||||
|
playerid = data['playerId']
|
||||||
|
|
||||||
|
# 调用分析接口（注：analysisMovieUrl 的响应可能也是加密的，但原脚本直接取 data，这里暂不做额外解密）
|
||||||
|
analysis_body = {
|
||||||
|
"playerUrl": parse_url,
|
||||||
|
"playerId": playerid
|
||||||
|
}
|
||||||
|
analysis_json = json.dumps(analysis_body, separators=(',', ':'))
|
||||||
|
# analysisMovieUrl 接口的参数拼接？理论上也需要签名，但原脚本是 GET 方式，为了兼容，我们沿用原脚本的 GET 方式
|
||||||
|
# 原脚本使用 fetch GET 带参数，并未加密。这里也采用 GET 方式，不使用加密 headers
|
||||||
|
resp_analysis = self.fetch(f"{self.host}/api/v1/app/play/analysisMovieUrl?playerUrl={quote(parse_url,safe='')}&playerId={playerid}", headers=self.headers).json()
|
||||||
|
url = resp_analysis.get('data')
|
||||||
|
|
||||||
|
return {'jx': '0', 'parse': '0', 'url': url, 'header': {'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1'}}
|
||||||
|
|
||||||
|
def getName(self):
|
||||||
|
pass
|
||||||
|
|
||||||
|
def isVideoFormat(self, url):
|
||||||
|
pass
|
||||||
|
|
||||||
|
def manualVideoCheck(self):
|
||||||
|
pass
|
||||||
|
|
||||||
|
def destroy(self):
|
||||||
|
pass
|
||||||
|
|
||||||
|
def localProxy(self, param):
|
||||||
|
pass
|
||||||
+336
@@ -0,0 +1,336 @@
|
|||||||
|
# -*- coding: utf-8 -*-
|
||||||
|
# by @PyramidStore AutoGen
|
||||||
|
import re
|
||||||
|
import sys
|
||||||
|
sys.path.append('..')
|
||||||
|
import json
|
||||||
|
from urllib.parse import quote
|
||||||
|
from base.spider import Spider
|
||||||
|
|
||||||
|
|
||||||
|
class Spider(Spider):
|
||||||
|
|
||||||
|
def init(self, extend=""):
|
||||||
|
self.nav_host = 'https://www.xiguadh.com'
|
||||||
|
self.headers = {
|
||||||
|
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||||
|
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
|
||||||
|
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
|
||||||
|
}
|
||||||
|
self.host = self._get_host()
|
||||||
|
|
||||||
|
def _get_host(self):
|
||||||
|
"""获取视频站点 URL，失败时从导航页获取"""
|
||||||
|
default_host = 'https://www.bzzdyy.com'
|
||||||
|
try:
|
||||||
|
r = self.fetch(default_host, headers=self.headers, timeout=10, verify=False)
|
||||||
|
if r.status_code == 200:
|
||||||
|
return default_host
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
try:
|
||||||
|
r = self.fetch(self.nav_host, headers=self.headers, timeout=15, verify=False)
|
||||||
|
html = r.text
|
||||||
|
urls = re.findall(r'url:\s*["\']([^"\']+)["\']', html)
|
||||||
|
for url in urls:
|
||||||
|
if url.startswith('http') and 'xiguadh' not in url:
|
||||||
|
return url.rstrip('/')
|
||||||
|
except Exception:
|
||||||
|
pass
|
||||||
|
return default_host
|
||||||
|
|
||||||
|
def getName(self):
|
||||||
|
return '西瓜影院'
|
||||||
|
|
||||||
|
def isVideoFormat(self, url):
|
||||||
|
return False
|
||||||
|
|
||||||
|
def manualVideoCheck(self):
|
||||||
|
return True
|
||||||
|
|
||||||
|
def homeContent(self, filter):
|
||||||
|
try:
|
||||||
|
r = self.fetch(self.host, headers=self.headers, timeout=15, verify=False)
|
||||||
|
html = r.text
|
||||||
|
# 提取主要分类
|
||||||
|
nav_match = re.search(r'<ul class="stui-header__menu">(.*?)</ul>', html, re.DOTALL)
|
||||||
|
if nav_match:
|
||||||
|
nav_html = nav_match.group(1)
|
||||||
|
categories = re.findall(r'<li[^>]*><a href="/index.php/vod/type/id/(\d+)\.html">([^<]+)</a></li>', nav_html)
|
||||||
|
else:
|
||||||
|
categories = []
|
||||||
|
seen = set()
|
||||||
|
classes = []
|
||||||
|
for tid, name in categories:
|
||||||
|
if tid not in seen:
|
||||||
|
seen.add(tid)
|
||||||
|
classes.append({'type_name': name, 'type_id': tid})
|
||||||
|
if not classes:
|
||||||
|
raise Exception('No categories found')
|
||||||
|
# 提取首页推荐视频
|
||||||
|
videos = self._parse_vodlist(html)
|
||||||
|
except Exception:
|
||||||
|
classes = [
|
||||||
|
{'type_name': '电影', 'type_id': '20'},
|
||||||
|
{'type_name': '连续剧', 'type_id': '37'},
|
||||||
|
{'type_name': '动漫', 'type_id': '43'},
|
||||||
|
{'type_name': '综艺', 'type_id': '45'},
|
||||||
|
{'type_name': 'B站', 'type_id': '47'},
|
||||||
|
{'type_name': '人人专区', 'type_id': '60'},
|
||||||
|
]
|
||||||
|
videos = []
|
||||||
|
return {"class": classes, "list": videos}
|
||||||
|
|
||||||
|
def _parse_vodlist(self, html):
|
||||||
|
"""解析视频列表"""
|
||||||
|
items = re.findall(
|
||||||
|
r'<a class="stui-vodlist__thumb[^"]*"\s+href="([^"]+)"\s+title="([^"]*)"[^>]*data-original="([^"]*)"',
|
||||||
|
html
|
||||||
|
)
|
||||||
|
videos = []
|
||||||
|
for href, title, pic in items:
|
||||||
|
vod_id = re.search(r'/id/(\d+)\.html', href)
|
||||||
|
if vod_id:
|
||||||
|
vod_id = vod_id.group(1)
|
||||||
|
else:
|
||||||
|
continue
|
||||||
|
remark_match = re.search(r'<span class="pic-text text-right"><b>([^<]+)</b></span>',
|
||||||
|
html[html.find(href):html.find(href)+500] if href in html else '')
|
||||||
|
remark = remark_match.group(1) if remark_match else ''
|
||||||
|
if pic.startswith('/'):
|
||||||
|
pic = self.host + pic
|
||||||
|
videos.append({
|
||||||
|
'vod_id': vod_id,
|
||||||
|
'vod_name': title,
|
||||||
|
'vod_pic': pic,
|
||||||
|
'vod_remarks': remark,
|
||||||
|
})
|
||||||
|
return videos
|
||||||
|
|
||||||
|
def homeVideoContent(self):
|
||||||
|
return ''
|
||||||
|
|
||||||
|
def categoryContent(self, tid, pg, filter, extend):
|
||||||
|
pg = int(pg)
|
||||||
|
url = f'{self.host}/index.php/vod/type/id/{tid}/page/{pg}.html'
|
||||||
|
try:
|
||||||
|
r = self.fetch(url, headers=self.headers, timeout=15, verify=False)
|
||||||
|
html = r.text
|
||||||
|
items = re.findall(
|
||||||
|
r'<a class="stui-vodlist__thumb[^"]*"\s+href="([^"]+)"\s+title="([^"]*)"[^>]*data-original="([^"]*)"',
|
||||||
|
html
|
||||||
|
)
|
||||||
|
videos = []
|
||||||
|
for href, title, pic in items:
|
||||||
|
vod_id = re.search(r'/id/(\d+)\.html', href)
|
||||||
|
if vod_id:
|
||||||
|
vod_id = vod_id.group(1)
|
||||||
|
else:
|
||||||
|
continue
|
||||||
|
remark_match = re.search(r'<span class="pic-text text-right"><b>([^<]+)</b></span>',
|
||||||
|
html[html.find(href):html.find(href)+500] if href in html else '')
|
||||||
|
remark = remark_match.group(1) if remark_match else ''
|
||||||
|
if pic.startswith('/'):
|
||||||
|
pic = self.host + pic
|
||||||
|
videos.append({
|
||||||
|
'vod_id': vod_id,
|
||||||
|
'vod_name': title,
|
||||||
|
'vod_pic': pic,
|
||||||
|
'vod_remarks': remark,
|
||||||
|
})
|
||||||
|
return {
|
||||||
|
"list": videos,
|
||||||
|
"page": pg,
|
||||||
|
"pagecount": 9999,
|
||||||
|
"limit": 90,
|
||||||
|
"total": len(videos),
|
||||||
|
}
|
||||||
|
except Exception as e:
|
||||||
|
return {"list": [], "page": pg, "pagecount": 1, "limit": 90, "total": 0}
|
||||||
|
|
||||||
|
def detailContent(self, ids):
|
||||||
|
try:
|
||||||
|
vod_id = ids[0] if isinstance(ids, list) else ids
|
||||||
|
url = f'{self.host}/index.php/vod/detail/id/{vod_id}.html'
|
||||||
|
r = self.fetch(url, headers=self.headers, timeout=15, verify=False)
|
||||||
|
html = r.text
|
||||||
|
title_match = re.search(r'<h1 class="title">([^<]+)</h1>', html)
|
||||||
|
title = title_match.group(1).strip() if title_match else ''
|
||||||
|
self._vod_name = title
|
||||||
|
pic_match = re.search(r'<img class="lazyload" data-original="([^"]*)"', html)
|
||||||
|
pic = pic_match.group(1) if pic_match else ''
|
||||||
|
if pic.startswith('/'):
|
||||||
|
pic = self.host + pic
|
||||||
|
info_match = re.search(r'类型：([^/]+)\s*/\s*地区：([^/]+)\s*/\s*年份：(\d+)', html)
|
||||||
|
type_name = info_match.group(1).strip() if info_match else ''
|
||||||
|
area = info_match.group(2).strip() if info_match else ''
|
||||||
|
year = info_match.group(3) if info_match else ''
|
||||||
|
remark_match = re.search(r'状态：<span[^>]*>([^<]+)</span>', html)
|
||||||
|
remark = remark_match.group(1).strip() if remark_match else ''
|
||||||
|
director_match = re.search(r'导演：(.*?)</p>', html, re.DOTALL)
|
||||||
|
director = ''
|
||||||
|
if director_match:
|
||||||
|
director = re.sub(r'<[^>]+>', '', director_match.group(1)).strip()
|
||||||
|
actor_match = re.search(r'主演：([^<]+)', html)
|
||||||
|
actor = actor_match.group(1).strip() if actor_match else ''
|
||||||
|
desc_match = re.search(r'<span class="detail-content"[^>]*>([^<]+)</span>', html)
|
||||||
|
desc = desc_match.group(1).strip() if desc_match else ''
|
||||||
|
play_from = []
|
||||||
|
play_url = []
|
||||||
|
source_tabs = re.findall(r'<li><a href="#playlist\d+"[^>]*>([^<]+)</a></li>', html)
|
||||||
|
for idx, source_name in enumerate(source_tabs):
|
||||||
|
source_id = idx + 1
|
||||||
|
episodes_match = re.search(
|
||||||
|
f'<div id="playlist{source_id}" class="tab-pane[^"]*"[^>]*>.*?<ul class="stui-content__playlist[^"]*"[^>]*>(.*?)</ul>',
|
||||||
|
html, re.DOTALL
|
||||||
|
)
|
||||||
|
if episodes_match:
|
||||||
|
episodes = re.findall(r'<a href="([^"]+)">([^<]+)</a>', episodes_match.group(1))
|
||||||
|
episode_list = []
|
||||||
|
for ep_url, ep_name in episodes:
|
||||||
|
episode_list.append(f'{ep_name}${self.host}{ep_url}')
|
||||||
|
play_from.append(source_name)
|
||||||
|
play_url.append('#'.join(episode_list))
|
||||||
|
vod_play_from = '$$$'.join(play_from) if play_from else '默认'
|
||||||
|
vod_play_url = '$$$'.join(play_url) if play_url else ''
|
||||||
|
vod = {
|
||||||
|
'vod_id': vod_id,
|
||||||
|
'vod_name': title,
|
||||||
|
'vod_pic': pic,
|
||||||
|
'vod_year': year,
|
||||||
|
'vod_area': area,
|
||||||
|
'vod_remarks': remark,
|
||||||
|
'vod_director': director,
|
||||||
|
'vod_actor': actor,
|
||||||
|
'vod_content': desc,
|
||||||
|
'vod_play_from': vod_play_from,
|
||||||
|
'vod_play_url': vod_play_url,
|
||||||
|
}
|
||||||
|
return {"list": [vod]}
|
||||||
|
except Exception as e:
|
||||||
|
return {"list": []}
|
||||||
|
|
||||||
|
def searchContent(self, key, quick, pg="1"):
|
||||||
|
pg = int(pg)
|
||||||
|
url = f'{self.host}/index.php/vod/search/wd/{quote(key)}.html'
|
||||||
|
try:
|
||||||
|
r = self.fetch(url, headers=self.headers, timeout=15, verify=False)
|
||||||
|
html = r.text
|
||||||
|
items = re.findall(
|
||||||
|
r'<a class="stui-vodlist__thumb[^"]*"\s+href="([^"]+)"\s+title="([^"]*)"[^>]*data-original="([^"]*)"',
|
||||||
|
html
|
||||||
|
)
|
||||||
|
videos = []
|
||||||
|
for href, title, pic in items:
|
||||||
|
vod_id = re.search(r'/id/(\d+)\.html', href)
|
||||||
|
if vod_id:
|
||||||
|
vod_id = vod_id.group(1)
|
||||||
|
else:
|
||||||
|
continue
|
||||||
|
remark_match = re.search(r'<span class="pic-text text-right"><b>([^<]+)</b></span>',
|
||||||
|
html[html.find(href):html.find(href)+500] if href in html else '')
|
||||||
|
remark = remark_match.group(1) if remark_match else ''
|
||||||
|
if pic.startswith('/'):
|
||||||
|
pic = self.host + pic
|
||||||
|
videos.append({
|
||||||
|
'vod_id': vod_id,
|
||||||
|
'vod_name': title,
|
||||||
|
'vod_pic': pic,
|
||||||
|
'vod_remarks': remark,
|
||||||
|
})
|
||||||
|
return {
|
||||||
|
"list": videos,
|
||||||
|
"page": pg,
|
||||||
|
"pagecount": 9999,
|
||||||
|
"limit": 90,
|
||||||
|
"total": len(videos),
|
||||||
|
}
|
||||||
|
except Exception as e:
|
||||||
|
return {"list": [], "page": pg, "pagecount": 1, "limit": 90, "total": 0}
|
||||||
|
|
||||||
|
def _clean_vod_name(self, name):
|
||||||
|
import re
|
||||||
|
if not name:
|
||||||
|
return ''
|
||||||
|
cleaned = re.sub(r'第\s*\d+\s*[集話话章部期]', '', name)
|
||||||
|
cleaned = re.sub(r'EP\s*\d+', '', cleaned, flags=re.IGNORECASE)
|
||||||
|
cleaned = re.sub(r'全\d+集', '', cleaned)
|
||||||
|
cleaned = re.sub(r'更新至\d+集', '', cleaned)
|
||||||
|
cleaned = re.sub(r'\d+集全', '', cleaned)
|
||||||
|
cleaned = re.sub(r'[（(].*?[）)]', '', cleaned)
|
||||||
|
cleaned = re.sub(r'\s*-\s*.*$', '', cleaned)
|
||||||
|
cleaned = re.sub(r'\s+', ' ', cleaned)
|
||||||
|
cleaned = re.sub(r'^[\s\-_,.，。、]+|[\s\-_,.，。、]+$', '', cleaned)
|
||||||
|
return cleaned.strip()
|
||||||
|
|
||||||
|
def _build_danmaku_url(self, vod_name, vod_index=''):
|
||||||
|
import re
|
||||||
|
idx = 0
|
||||||
|
if vod_index:
|
||||||
|
s = str(vod_index).strip()
|
||||||
|
m = re.search(r'第\s*(\d+)\s*[集話话章部期]', s)
|
||||||
|
if m:
|
||||||
|
idx = int(m.group(1))
|
||||||
|
else:
|
||||||
|
m = re.search(r'(\d+)', s)
|
||||||
|
if m:
|
||||||
|
idx = int(m.group(1))
|
||||||
|
cleaned_name = self._clean_vod_name(vod_name)
|
||||||
|
params = []
|
||||||
|
if cleaned_name:
|
||||||
|
params.append(f'vodName={quote(cleaned_name)}')
|
||||||
|
params.append(f'vodIndex={idx}')
|
||||||
|
query = '&'.join(params)
|
||||||
|
return f'http://127.0.0.1:9978/proxy?do=appdanmu&{query}'
|
||||||
|
|
||||||
|
def playerContent(self, flag, id, vipFlags):
|
||||||
|
try:
|
||||||
|
ep_name = ''
|
||||||
|
vod_index = ''
|
||||||
|
if '$' in id:
|
||||||
|
parts = id.split('$', 1)
|
||||||
|
ep_name = parts[0]
|
||||||
|
url = parts[1] if len(parts) > 1 else ''
|
||||||
|
else:
|
||||||
|
url = id if id.startswith('http') else f'{self.host}{id}'
|
||||||
|
# 从 URL 中提取集数 (nid 参数)
|
||||||
|
nid_match = re.search(r'nid/(\d+)\.html', url)
|
||||||
|
if nid_match:
|
||||||
|
vod_index = nid_match.group(1)
|
||||||
|
danmaku_url = self._build_danmaku_url(self._vod_name, vod_index)
|
||||||
|
r = self.fetch(url, headers=self.headers, timeout=15, verify=False)
|
||||||
|
html = r.text
|
||||||
|
iframe_match = re.search(r'<iframe[^>]+src="([^"]+)"', html)
|
||||||
|
if iframe_match:
|
||||||
|
iframe_url = iframe_match.group(1)
|
||||||
|
if not iframe_url.startswith('http'):
|
||||||
|
iframe_url = self.host + iframe_url
|
||||||
|
return {
|
||||||
|
"parse": 1,
|
||||||
|
"url": iframe_url,
|
||||||
|
"header": self.headers,
|
||||||
|
"danmaku": danmaku_url
|
||||||
|
}
|
||||||
|
src_match = re.search(r'(https?://[^"\'<>\s]+\.m3u8[^"\'<>\s]*)', html)
|
||||||
|
if src_match:
|
||||||
|
return {
|
||||||
|
"parse": 0,
|
||||||
|
"url": src_match.group(1),
|
||||||
|
"header": self.headers,
|
||||||
|
"danmaku": danmaku_url
|
||||||
|
}
|
||||||
|
return {
|
||||||
|
"parse": 1,
|
||||||
|
"url": url,
|
||||||
|
"header": self.headers,
|
||||||
|
"danmaku": danmaku_url
|
||||||
|
}
|
||||||
|
except Exception as e:
|
||||||
|
danmaku_url = self._build_danmaku_url(self._vod_name, '')
|
||||||
|
return {"parse": 1, "url": id, "header": {}, "danmaku": danmaku_url}
|
||||||
|
|
||||||
|
def localProxy(self, param):
|
||||||
|
return [200, {}, ""]
|
||||||
|
|
||||||
|
def destroy(self):
|
||||||
|
pass
|
||||||
Reference in New Issue
Block a user