樱花动漫
This commit is contained in:
Harold
@@ -0,0 +1,236 @@
|
||||
import unittest
|
||||
from importlib.machinery import SourceFileLoader
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
MODULE = SourceFileLoader("yinghua_spider", str(ROOT / "樱花动漫.py")).load_module()
|
||||
Spider = MODULE.Spider
|
||||
|
||||
|
||||
SAMPLE_DETAIL_HTML = """
|
||||
<html><body>
|
||||
<div class="detail"><h2>进击的巨人</h2></div>
|
||||
<div class="cover"><img data-original="https://pic.example.com/zr.jpg" /></div>
|
||||
<div class="item"><span>状态:</span><em>已完结</em></div>
|
||||
<div class="item"><span>年份:</span>2023</div>
|
||||
<div class="item"><span>地区:</span>日本</div>
|
||||
<div class="item"><span>类型:</span>热血</div>
|
||||
<div class="item"><span>主演:</span>梶裕贵</div>
|
||||
<li class="blurb"><span>简介</span>讲述巨人的故事</li>
|
||||
<div class="module-tab-item">高清</div>
|
||||
<div class="module-tab-item">ikun</div>
|
||||
<div class="module-play-list">
|
||||
<a href="/play/12345-1-1/">第01集</a>
|
||||
<a href="/play/12345-1-2/">第02集</a>
|
||||
<a href="/play/12345-1-3/">第03集</a>
|
||||
</div>
|
||||
<div class="module-play-list">
|
||||
<a href="/play/12345-2-1/">第01集</a>
|
||||
<a href="/play/12345-2-2/">第02集</a>
|
||||
</div>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
SAMPLE_LIST_HTML = """
|
||||
<html><body>
|
||||
<ul>
|
||||
<li><a href="/detail/123/" title="进击的巨人"><img data-original="https://pic/1.jpg" /></a><p>已完结</p></li>
|
||||
<li><a href="/detail/456/" title="鬼灭之刃"><img data-original="https://pic/2.jpg" /></a><p>更新中</p></li>
|
||||
<li><a href="/other/" title="忽略项"></a></li>
|
||||
</ul>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
SAMPLE_SEARCH_HTML = """
|
||||
<html><body>
|
||||
找到 <em>5</em> 条结果
|
||||
<ul>
|
||||
<li><a class="cover" href="/detail/123/" title="进击的巨人" data-original="https://pic/1.jpg">
|
||||
<div class="item"><span>状态:</span>已完结</div>
|
||||
</a></li>
|
||||
<li><a class="cover" href="/detail/456/" title="鬼灭之刃" data-original="https://pic/2.jpg">
|
||||
<div class="item"><span>状态:</span>更新中</div>
|
||||
</a></li>
|
||||
</ul>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
SAMPLE_PLAY_HTML = """
|
||||
<html><body>
|
||||
<script>
|
||||
var art = new Artplayer({
|
||||
url: 'https://cdn.example.com/video/12345.m3u8?key=abc',
|
||||
});
|
||||
</script>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
SAMPLE_CATEGORY_HTML = """
|
||||
<html><body>
|
||||
<ul>
|
||||
<li><a href="/detail/123/" title="进击的巨人"><img data-original="https://pic/1.jpg" /></a><p>已完结</p></li>
|
||||
</ul>
|
||||
<div class="pagination">
|
||||
<a href="/type/riman/3/">3</a>
|
||||
<a href="/type/riman/5/">5</a>
|
||||
</div>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
|
||||
class TestYingHuaSpider(unittest.TestCase):
|
||||
def setUp(self):
|
||||
Spider._instance = None
|
||||
self.spider = Spider()
|
||||
self.spider.init()
|
||||
|
||||
def test_home_content_classes(self):
|
||||
content = self.spider.homeContent(False)
|
||||
ids = [c["type_id"] for c in content["class"]]
|
||||
self.assertEqual(len(content["class"]), 4)
|
||||
self.assertIn("guoman", ids)
|
||||
self.assertIn("riman", ids)
|
||||
self.assertIn("oman", ids)
|
||||
self.assertIn("dmfilm", ids)
|
||||
|
||||
def test_get_name(self):
|
||||
self.assertEqual(self.spider.getName(), "樱花动漫")
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_home_video_content(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_LIST_HTML
|
||||
result = self.spider.homeVideoContent()
|
||||
self.assertEqual(len(result["list"]), 2)
|
||||
self.assertEqual(result["list"][0]["vod_name"], "进击的巨人")
|
||||
self.assertEqual(result["list"][0]["vod_remarks"], "已完结")
|
||||
self.assertEqual(result["list"][1]["vod_name"], "鬼灭之刃")
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_home_video_dedup(self, mock_html):
|
||||
mock_html.return_value = """
|
||||
<ul>
|
||||
<li><a href="/detail/123/" title="A"><img src="p.jpg" /></a></li>
|
||||
<li><a href="/detail/123/" title="A"><img src="p.jpg" /></a></li>
|
||||
</ul>
|
||||
"""
|
||||
result = self.spider.homeVideoContent()
|
||||
self.assertEqual(len(result["list"]), 1)
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_category_content(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_CATEGORY_HTML
|
||||
result = self.spider.categoryContent("riman", "1", False, {})
|
||||
self.assertEqual(len(result["list"]), 1)
|
||||
self.assertEqual(result["list"][0]["vod_name"], "进击的巨人")
|
||||
self.assertEqual(result["pagecount"], 5)
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_category_page2_url(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_LIST_HTML
|
||||
self.spider.categoryContent("riman", "2", False, {})
|
||||
mock_html.assert_called_with("https://www.dmvvv.com/type/riman/2/")
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_detail_content(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_DETAIL_HTML
|
||||
result = self.spider.detailContent(["/detail/12345/"])
|
||||
vod = result["list"][0]
|
||||
self.assertEqual(vod["vod_name"], "进击的巨人")
|
||||
self.assertEqual(vod["vod_pic"], "https://pic.example.com/zr.jpg")
|
||||
self.assertEqual(vod["vod_remarks"], "已完结")
|
||||
self.assertEqual(vod["vod_year"], "2023")
|
||||
self.assertEqual(vod["vod_area"], "日本")
|
||||
self.assertEqual(vod["vod_content"], "讲述巨人的故事")
|
||||
self.assertIn("高清", vod["vod_play_from"])
|
||||
self.assertIn("ikun", vod["vod_play_from"])
|
||||
self.assertIn("第01集$/play/12345-1-1/", vod["vod_play_url"])
|
||||
self.assertIn("第02集$/play/12345-1-2/", vod["vod_play_url"])
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_detail_multi_source_grouping(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_DETAIL_HTML
|
||||
result = self.spider.detailContent(["/detail/12345/"])
|
||||
vod = result["list"][0]
|
||||
from_list = vod["vod_play_from"].split("$$$")
|
||||
url_groups = vod["vod_play_url"].split("$$$")
|
||||
self.assertEqual(len(from_list), 2)
|
||||
self.assertEqual(len(url_groups), 2)
|
||||
# 高清 source (sourceIdx=1)
|
||||
self.assertEqual(from_list[0], "高清")
|
||||
self.assertIn("第01集$/play/12345-1-1/", url_groups[0])
|
||||
self.assertIn("第03集$/play/12345-1-3/", url_groups[0])
|
||||
# ikun source (sourceIdx=2)
|
||||
self.assertEqual(from_list[1], "ikun")
|
||||
self.assertIn("第01集$/play/12345-2-1/", url_groups[1])
|
||||
self.assertIn("第02集$/play/12345-2-2/", url_groups[1])
|
||||
# ensure no cross-contamination
|
||||
self.assertNotIn("12345-2-", url_groups[0])
|
||||
self.assertNotIn("12345-1-", url_groups[1])
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_detail_title_from_title_tag(self, mock_html):
|
||||
mock_html.return_value = "<html><body><title>鬼灭之刃 - 樱花动漫</title></body></html>"
|
||||
result = self.spider.detailContent(["/detail/999/"])
|
||||
vod = result["list"][0]
|
||||
self.assertEqual(vod["vod_name"], "鬼灭之刃")
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_detail_no_episodes(self, mock_html):
|
||||
mock_html.return_value = """
|
||||
<html><body>
|
||||
<div class="detail"><h2>测试</h2></div>
|
||||
</body></html>
|
||||
"""
|
||||
result = self.spider.detailContent(["/detail/1/"])
|
||||
vod = result["list"][0]
|
||||
self.assertEqual(vod["vod_play_from"], "default")
|
||||
self.assertEqual(vod["vod_play_url"], "")
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_search_content(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_SEARCH_HTML
|
||||
result = self.spider.searchContent("巨人", False, "1")
|
||||
self.assertEqual(len(result["list"]), 2)
|
||||
self.assertEqual(result["list"][0]["vod_name"], "进击的巨人")
|
||||
self.assertEqual(result["pagecount"], 1)
|
||||
|
||||
def test_search_empty_keyword(self):
|
||||
result = self.spider.searchContent("", False, "1")
|
||||
self.assertEqual(result["list"], [])
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_search_quick_mode(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_SEARCH_HTML
|
||||
result = self.spider.searchContent("巨人", True, "1")
|
||||
self.assertEqual(len(result["list"]), 2)
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_player_content_artplayer(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_PLAY_HTML
|
||||
result = self.spider.playerContent("高清", "/play/12345-1-1/", {})
|
||||
self.assertEqual(result["parse"], 0)
|
||||
self.assertEqual(result["url"], "https://cdn.example.com/video/12345.m3u8?key=abc")
|
||||
self.assertIn("Referer", result["header"])
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_player_content_m3u8_fallback(self, mock_html):
|
||||
mock_html.return_value = '<html><script>var src = "https://cdn.example.com/stream.m3u8";</script></html>'
|
||||
result = self.spider.playerContent("高清", "/play/12345-1-1/", {})
|
||||
self.assertEqual(result["url"], "https://cdn.example.com/stream.m3u8")
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_player_content_no_match(self, mock_html):
|
||||
mock_html.return_value = "<html><body>no video</body></html>"
|
||||
result = self.spider.playerContent("高清", "/play/12345-1-1/", {})
|
||||
self.assertEqual(result["url"], "https://www.dmvvv.com/play/12345-1-1/")
|
||||
|
||||
@patch.object(Spider, "_get_html")
|
||||
def test_detail_full_url(self, mock_html):
|
||||
mock_html.return_value = SAMPLE_DETAIL_HTML
|
||||
self.spider.detailContent(["https://www.dmvvv.com/detail/12345/"])
|
||||
mock_html.assert_called_with("https://www.dmvvv.com/detail/12345/")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
+283
@@ -0,0 +1,283 @@
|
||||
# coding=utf-8
|
||||
import re
|
||||
import sys
|
||||
from urllib.parse import quote
|
||||
|
||||
from base.spider import Spider as BaseSpider
|
||||
|
||||
sys.path.append("..")
|
||||
|
||||
|
||||
class Spider(BaseSpider):
|
||||
def __init__(self):
|
||||
self.name = "樱花动漫"
|
||||
self.host = "https://www.dmvvv.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"
|
||||
),
|
||||
"Referer": "https://www.dmvvv.com/",
|
||||
"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.classes = [
|
||||
{"type_id": "guoman", "type_name": "国产动漫"},
|
||||
{"type_id": "riman", "type_name": "日本动漫"},
|
||||
{"type_id": "oman", "type_name": "欧美动漫"},
|
||||
{"type_id": "dmfilm", "type_name": "动漫电影"},
|
||||
]
|
||||
|
||||
def init(self, extend=""):
|
||||
return None
|
||||
|
||||
def getName(self):
|
||||
return self.name
|
||||
|
||||
def homeContent(self, filter):
|
||||
return {"class": self.classes}
|
||||
|
||||
def homeVideoContent(self):
|
||||
html = self._get_html(self.host + "/")
|
||||
items = self._parse_list(html)
|
||||
seen = set()
|
||||
unique = []
|
||||
for item in items:
|
||||
if item["vod_id"] not in seen:
|
||||
seen.add(item["vod_id"])
|
||||
unique.append(item)
|
||||
return {"list": unique[:20]}
|
||||
|
||||
def categoryContent(self, tid, pg, filter, extend):
|
||||
page = int(pg)
|
||||
url = f"{self.host}/type/{tid}/" if page <= 1 else f"{self.host}/type/{tid}/{page}/"
|
||||
html = self._get_html(url)
|
||||
items = self._parse_list(html)
|
||||
pagecount = self._parse_page_count(html, tid)
|
||||
if pagecount <= page and len(items) >= 36:
|
||||
pagecount = page + 1
|
||||
return {
|
||||
"list": items,
|
||||
"page": page,
|
||||
"pagecount": pagecount,
|
||||
"total": pagecount * len(items) if items else 0,
|
||||
}
|
||||
|
||||
def detailContent(self, ids):
|
||||
raw_id = ids[0] if isinstance(ids, list) else ids
|
||||
url = raw_id if raw_id.startswith("http") else self.host + raw_id
|
||||
html = self._get_html(url)
|
||||
vod = self._parse_detail(html, raw_id)
|
||||
return {"list": [vod] if vod else []}
|
||||
|
||||
def searchContent(self, key, quick, pg="1"):
|
||||
page = int(pg)
|
||||
keyword = key.strip()
|
||||
if not keyword:
|
||||
return {"list": [], "page": page, "pagecount": 0, "total": 0}
|
||||
encoded = quote(keyword)
|
||||
url = (
|
||||
f"{self.host}/search/?wd={encoded}"
|
||||
if page <= 1
|
||||
else f"{self.host}/search/?wd={encoded}&pageno={page}"
|
||||
)
|
||||
html = self._get_html(url)
|
||||
items = self._parse_search_list(html)
|
||||
pagecount = self._parse_search_page_count(html, page, len(items))
|
||||
return {
|
||||
"list": items[:10] if quick else items,
|
||||
"page": page,
|
||||
"pagecount": pagecount,
|
||||
"total": len(items),
|
||||
}
|
||||
|
||||
def playerContent(self, flag, id, vipFlags):
|
||||
url = id if id.startswith("http") else self.host + id
|
||||
html = self._get_html(url)
|
||||
play_url = self._extract_play_url(html, url)
|
||||
return {
|
||||
"parse": 0,
|
||||
"url": play_url,
|
||||
"header": {
|
||||
"User-Agent": self.headers["User-Agent"],
|
||||
"Referer": self.host + "/",
|
||||
},
|
||||
}
|
||||
|
||||
# --- helpers ---
|
||||
|
||||
def _s(self, val):
|
||||
return "" if val is None else str(val).strip()
|
||||
|
||||
def _get_html(self, url):
|
||||
rsp = self.fetch(url, headers=self.headers, timeout=15, verify=False)
|
||||
if rsp.status_code != 200:
|
||||
return ""
|
||||
return rsp.text or ""
|
||||
|
||||
def _parse_list(self, html):
|
||||
root = self.html(html)
|
||||
if root is None:
|
||||
return []
|
||||
items = []
|
||||
for li in root.xpath("//li"):
|
||||
link = li.xpath(".//a[@href]")
|
||||
if not link:
|
||||
continue
|
||||
href = self._s(link[0].get("href", ""))
|
||||
title = self._s(link[0].get("title", ""))
|
||||
if not href or "/detail/" not in href or not title:
|
||||
continue
|
||||
pic = self._s((li.xpath(".//img/@data-original") or li.xpath(".//img/@src") or [""])[0])
|
||||
remarks = self._s((li.xpath(".//p//text()") or [""])[0])
|
||||
items.append({
|
||||
"vod_id": href,
|
||||
"vod_name": title,
|
||||
"vod_pic": pic,
|
||||
"vod_remarks": remarks,
|
||||
})
|
||||
return items
|
||||
|
||||
def _parse_search_list(self, html):
|
||||
items = []
|
||||
pattern = re.compile(r'<a class="cover" href="(/detail/\d+/)"', re.S)
|
||||
for block in re.finditer(r"<li>\s*<a class=\"cover\".*?</li>", html, re.S):
|
||||
chunk = block.group(0)
|
||||
href_m = pattern.search(chunk)
|
||||
if not href_m:
|
||||
continue
|
||||
title_m = re.search(r'title="([^"]+)"', chunk)
|
||||
cover_m = re.search(r'data-original="([^"]+)"', chunk)
|
||||
remark_m = re.search(r'<div class="item"><span>状态:</span>([^<]*)', chunk)
|
||||
if not title_m:
|
||||
continue
|
||||
items.append({
|
||||
"vod_id": href_m.group(1),
|
||||
"vod_name": title_m.group(1).strip(),
|
||||
"vod_pic": cover_m.group(1).strip() if cover_m else "",
|
||||
"vod_remarks": remark_m.group(1).strip() if remark_m else "",
|
||||
})
|
||||
return items
|
||||
|
||||
def _parse_page_count(self, html, tid):
|
||||
max_page = 1
|
||||
for m in re.finditer(r"/type/[^/]+/(\d+)/", html):
|
||||
max_page = max(max_page, int(m.group(1)))
|
||||
for m in re.finditer(r"[?&]page(?:no)?=(\d+)", html):
|
||||
max_page = max(max_page, int(m.group(1)))
|
||||
return max_page
|
||||
|
||||
def _parse_search_page_count(self, html, current_page, result_count):
|
||||
total_m = re.search(r"找到\s*<em>(\d+)</em>", html)
|
||||
if total_m:
|
||||
return max(1, -(-int(total_m.group(1)) // 12))
|
||||
max_page = current_page
|
||||
for m in re.finditer(r"pageno=(\d+)", html):
|
||||
max_page = max(max_page, int(m.group(1)))
|
||||
if max_page == current_page and result_count >= 12:
|
||||
return current_page + 1
|
||||
return max(max_page, 1)
|
||||
|
||||
def _parse_detail(self, html, raw_id):
|
||||
root = self.html(html)
|
||||
if root is None:
|
||||
return None
|
||||
title = ""
|
||||
title_m = re.search(r'<div class="detail">.*?<h2>([^<]+)</h2>', html, re.S)
|
||||
if title_m:
|
||||
title = title_m.group(1).strip()
|
||||
if not title:
|
||||
title_m2 = re.search(r"<title>([^<]+)", html)
|
||||
if title_m2:
|
||||
title = title_m2.group(1).split("-")[0].strip()
|
||||
|
||||
cover = ""
|
||||
cover_m = re.search(r'<div class="cover">\s*<img[^>]+data-original="([^"]+)"', html, re.S)
|
||||
if cover_m:
|
||||
cover = cover_m.group(1)
|
||||
|
||||
def get_info(label, use_em=True):
|
||||
pat = rf'<span>{label}:</span><em>([^<]+)</em>' if use_em else rf'<span>{label}:</span>([^<]+)'
|
||||
m = re.search(pat, html)
|
||||
return m.group(1).strip() if m else ""
|
||||
|
||||
vod_remarks = get_info("状态", True)
|
||||
vod_year = get_info("年份", False)
|
||||
vod_area = get_info("地区", False)
|
||||
vod_type = get_info("类型", False)
|
||||
vod_actor = get_info("主演", False)
|
||||
|
||||
vod_content = ""
|
||||
desc_m = re.search(r'class="blurb"[^>]*>.*?<span>[^<]+</span>(.*?)</li>', html, re.S)
|
||||
if desc_m:
|
||||
vod_content = re.sub(r"<[^>]+>", "", desc_m.group(1)).strip()
|
||||
|
||||
play_data = self._parse_play_sources(html, raw_id)
|
||||
|
||||
return {
|
||||
"vod_id": raw_id,
|
||||
"vod_name": title,
|
||||
"vod_pic": cover,
|
||||
"vod_year": vod_year,
|
||||
"vod_area": vod_area,
|
||||
"vod_type": vod_type,
|
||||
"vod_actor": vod_actor,
|
||||
"vod_remarks": vod_remarks,
|
||||
"vod_content": vod_content,
|
||||
"vod_play_from": play_data["vod_play_from"],
|
||||
"vod_play_url": play_data["vod_play_url"],
|
||||
}
|
||||
|
||||
def _parse_play_sources(self, html, raw_id):
|
||||
root = self.html(html)
|
||||
if root is None:
|
||||
return {"vod_play_from": "default", "vod_play_url": ""}
|
||||
source_names = ["高清", "ikun", "非凡", "量子"]
|
||||
# collect tab names in order
|
||||
tabs = []
|
||||
for idx, tab in enumerate(root.xpath("//*[contains(@class,'module-tab-item') or contains(@class,'tab-item')]")):
|
||||
name = self._s(tab.xpath("string(.)")).strip()
|
||||
if not name:
|
||||
name = source_names[idx] if idx < len(source_names) else f"线路{idx+1}"
|
||||
tabs.append(name)
|
||||
# group episodes by source index from URL: /play/{vid}-{sourceIdx}-{epIdx}/
|
||||
grouped = {}
|
||||
all_links = root.xpath("//*[contains(@class,'module-play-list')]//a[@href] | //*[contains(@class,'playlist')]//a[@href]")
|
||||
# fallback: try all links under .scroll-content or .module-list
|
||||
if not all_links:
|
||||
all_links = root.xpath("//*[contains(@class,'scroll-content') or contains(@class,'module-list')]//a[@href]")
|
||||
for a in all_links:
|
||||
ep_name = self._s(a.xpath("string(.)")).strip()
|
||||
ep_url = self._s(a.get("href", ""))
|
||||
if not ep_name or not ep_url or ep_url.startswith(("javascript:", "#")):
|
||||
continue
|
||||
m = re.search(r"/play/\d+-(\d+)-\d+/", ep_url)
|
||||
if m:
|
||||
src_idx = int(m.group(1)) - 1
|
||||
else:
|
||||
src_idx = 0
|
||||
if src_idx not in grouped:
|
||||
grouped[src_idx] = []
|
||||
grouped[src_idx].append(f"{ep_name}${ep_url}")
|
||||
if not grouped:
|
||||
return {"vod_play_from": "default", "vod_play_url": ""}
|
||||
# build output ordered by source index
|
||||
play_from = []
|
||||
play_url = []
|
||||
for src_idx in sorted(grouped.keys()):
|
||||
name = tabs[src_idx] if src_idx < len(tabs) else (source_names[src_idx] if src_idx < len(source_names) else f"线路{src_idx+1}")
|
||||
play_from.append(name)
|
||||
play_url.append("#".join(grouped[src_idx]))
|
||||
return {
|
||||
"vod_play_from": "$$$".join(play_from),
|
||||
"vod_play_url": "$$$".join(play_url),
|
||||
}
|
||||
|
||||
def _extract_play_url(self, html, fallback_url):
|
||||
m = re.search(r"url:\s*'(https?://[^']+)'", html)
|
||||
if m:
|
||||
return m.group(1)
|
||||
m = re.search(r"(https?://[^\s'\"<>]+\.m3u8(?:\?[^\s'\"<>]*)?)", html)
|
||||
if m:
|
||||
return m.group(1)
|
||||
return fallback_url
|
||||
Reference in New Issue
Block a user