diff --git a/py/一锅烩.py b/py/一锅烩.py index 5d76787..dbf42ea 100644 --- a/py/一锅烩.py +++ b/py/一锅烩.py @@ -1,3 +1,8 @@ +import urllib.request +from urllib.parse import urlparse +import re #正则 +import os +from datetime import datetime import requests # 定义txt文件的URL列表 urls = [ @@ -42,3 +47,359 @@ def merge_txt_files(urls, output_filename='汇总.txt'): print(f'Error writing to file: {e}') # 调用函数 merge_txt_files(urls) + + + +def remove_duplicates(input_file, output_file): + # 用于存储已经遇到的URL和包含genre的行 + seen_urls = set() + seen_lines_with_genre = set() + # 用于存储最终输出的行 + output_lines = [] + # 打开输入文件并读取所有行 + with open(input_file, 'r', encoding='utf-8') as f: + lines = f.readlines() + print("去重前的行数：", len(lines)) + # 遍历每一行 + for line in lines: + # 使用正则表达式查找URL和包含genre的行,默认最后一行 + urls = re.findall(r'[https]?[http]?[rtsp]?[rtmp]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', line) + genre_line = re.search(r'\bgenre\b', line, re.IGNORECASE) is not None + # 如果找到URL并且该URL尚未被记录 + if urls and urls[0] not in seen_urls: + seen_urls.add(urls[0]) + output_lines.append(line) + # 如果找到包含genre的行，无论是否已被记录，都写入新文件 + if genre_line: + output_lines.append(line) + # 将结果写入输出文件 + with open(output_file, 'w', encoding='utf-8') as f: + f.writelines(output_lines) + print("去重后的行数：", len(output_lines)) +# 使用方法 +remove_duplicates('汇总.txt', '汇总.txt') + +# 导入fileinput模块 +import fileinput +# 定义替换规则的字典 +replacements = { + "CCTV-1高清测试": "", + "CCTV-2高清测试": "", + "CCTV-7高清测试": "", + "CCTV-10高清测试": "", + "中央": "CCTV", + "高清""": "", + "HD": "", + "标清": "", + "-": "", + "超清": "", + "频道": "", + "CCTV-": "CCTV", + "CCTV_": "CCTV", + " ": "", + "CCTV风云剧场": "风云剧场", + "CCTV第一剧场": "第一剧场", + "CCTV怀旧剧场": "怀旧剧场", + "熊猫影院": "熊猫电影", + "熊猫爱生活": "熊猫生活", + "爱宠宠物": "宠物生活", + "[ipv6]": "", + "专区": "", + "卫视超": "卫视", + "CCTV风云剧场": "风云剧场", + "CCTV第一剧场": "第一剧场", + "CCTV怀旧剧场": "怀旧剧场", + "IPTV": "", + "PLUS": "+", + "＋": "+", + "(": "", + ")": "", + "CAV": "", + "美洲": "", + "北美": "", + "12M": "", + "高清测试CCTV-1": "", + "高清测试CCTV-2": "", + "高清测试CCTV-7": "", + "高清测试CCTV-10": "", + "LD": "", + "HEVC20M": "", + "S,": ",", + "测试": "", + "CCTW": "CCTV", + "试看": "", + "测试": "", + "测试cctv": "CCTV", + "CCTV1综合": "CCTV1", + "CCTV2财经": "CCTV2", + "CCTV3综艺": "CCTV3", + "CCTV4国际": "CCTV4", + "CCTV4中文国际": "CCTV4", + "CCTV4欧洲": "CCTV4", + "CCTV5体育": "CCTV5", + "CCTV5+体育": "CCTV5+", + "CCTV6电影": "CCTV6", + "CCTV7军事": "CCTV7", + "CCTV7军农": "CCTV7", + "CCTV7农业": "CCTV7", + "CCTV7国防军事": "CCTV7", + "CCTV8电视剧": "CCTV8", + "CCTV8影视": "CCTV8", + "CCTV8纪录": "CCTV9", + "CCTV9记录": "CCTV9", + "CCTV9纪录": "CCTV9", + "CCTV10科教": "CCTV10", + "CCTV11戏曲": "CCTV11", + "CCTV12社会与法": "CCTV12", + "CCTV13新闻": "CCTV13", + "CCTV新闻": "CCTV13", + "CCTV14少儿": "CCTV14", + "央视14少儿": "CCTV14", + "CCTV少儿超": "CCTV14", + "CCTV15音乐": "CCTV15", + "CCTV音乐": "CCTV15", + "CCTV16奥林匹克": "CCTV16", + "CCTV17农业农村": "CCTV17", + "CCTV17军农": "CCTV17", + "CCTV17农业": "CCTV17", + "CCTV5+体育赛视": "CCTV5+", + "CCTV5+赛视": "CCTV5+", + "CCTV5+体育赛事": "CCTV5+", + "CCTV5+赛事": "CCTV5+", + "CCTV5+体育": "CCTV5+", + "CCTV5赛事": "CCTV5+", + "凤凰中文台": "凤凰中文", + "凤凰资讯台": "凤凰资讯", + "(CCTV4K测试）": "CCTV4K", + "上海东方卫视": "上海卫视", + "东方卫视": "上海卫视", + "内蒙卫视": "内蒙古卫视", + "福建东南卫视": "东南卫视", + "广东南方卫视": "南方卫视", + "湖南金鹰卡通": "金鹰卡通", + "炫动卡通": "哈哈炫动", + "卡酷卡通": "卡酷少儿", + "卡酷动画": "卡酷少儿", + "BRTVKAKU少儿": "卡酷少儿", + "优曼卡通": "优漫卡通", + "优曼卡通": "优漫卡通", + "嘉佳卡通": "佳嘉卡通", + "世界地理": "地理世界", + "CCTV世界地理": "地理世界", + "BTV北京卫视": "北京卫视", + "BTV冬奥纪实": "冬奥纪实", + "东奥纪实": "冬奥纪实", + "卫视台": "卫视", + "湖南电视台": "湖南卫视", + "少儿科教": "少儿", + "影视剧": "影视", + "电视剧": "影视", + "CCTV1CCTV1": "CCTV1", + "CCTV2CCTV2": "CCTV2", + "CCTV7CCTV7": "CCTV7", + "CCTV10CCTV10": "CCTV10" +} +# 打开原始文件读取内容，并写入新文件 +with open('汇总.txt', 'r', encoding='utf-8') as file: + lines = file.readlines() +# 创建新文件并写入替换后的内容 +with open('汇总.txt', 'w', encoding='utf-8') as new_file: + for line in lines: + for old, new in replacements.items(): + line = line.replace(old, new) + new_file.write(line) +print("替换完成，新文件已保存。") + + + + +import re +from pypinyin import lazy_pinyin +# 打开一个utf-8编码的文本文件 +with open("汇总.txt", "r", encoding="utf-8") as file: + # 读取所有行并存储到列表中 + lines = file.readlines() +# 定义一个函数，用于提取每行的第一个数字 +def extract_first_number(line): + match = re.search(r'\d+', line) + return int(match.group()) if match else float('inf') +# 对列表中的行进行排序，按照第一个数字的大小排列，其余行按中文排序 +sorted_lines = sorted(lines, key=lambda x: (not 'CCTV' in x, extract_first_number(x) if 'CCTV' in x else lazy_pinyin(x.strip()))) +# 将排序后的行写入新的utf-8编码的文本文件 +with open("2.txt", "w", encoding="utf-8") as file: + for line in sorted_lines: + file.write(line) + + +import re +import os +def filter_lines(file_path): + with open(input_file_path, 'r', encoding='utf-8') as file: + lines = file.readlines() + filtered_lines = [] + for line in lines: + if ',' in line: + if 'epg' not in line and 'mitv' not in line and 'udp' not in line and 'rtp' not in line and 'tsfile' not in line and '/hls/' not in line \ + and 'P2p' not in line and 'p2p' not in line and 'p3p' not in line and 'P2P' not in line and 'P3p' not in line and 'P3P' not in line: + filtered_lines.append(line) + return filtered_lines +def write_filtered_lines(output_file_path, filtered_lines): + with open(output_file_path, 'w', encoding='utf-8') as output_file: + output_file.writelines(filtered_lines) +if __name__ == "__main__": + input_file_path = "2.txt" + output_file_path = "2.txt" + filtered_lines = filter_lines(input_file_path) + write_filtered_lines(output_file_path, filtered_lines) +print(f"文件已过滤完成") + + + +######################################################################################################################################################################################## +################################################################定义关键词分割规则 +def check_and_write_file(input_file, output_file, keywords): + # 使用 split(', ') 来分割关键词 + keywords_list = keywords.split(', ') + pattern = '|'.join(re.escape(keyword) for keyword in keywords_list) + + # 读取输入文件并提取包含关键词的行 + extracted_lines = [] + with open(input_file, 'r', encoding='utf-8') as file: + for line in file: + if "genre" not in line: + if re.search(pattern, line): + extracted_lines.append(line) + + # 如果至少提取到一行，写入头部信息和提取的行到输出文件 + if extracted_lines: + with open(output_file, 'w', encoding='utf-8') as out_file: + out_file.write(f"{keywords_list[0]},#genre#\n") # 写入头部信息 + out_file.writelines(extracted_lines) # 写入提取的行 + + # 获取头部信息的大小 + header_size = len(f"{keywords_list[0]},#genre#\n") + + # 检查文件的总大小 + file_size = os.path.getsize(output_file) + + # 如果文件大小小于30字节（假设的最小文件大小），删除文件 + if file_size < 800: + os.remove(output_file) + print(f"文件只包含头部信息，{output_file} 已被删除。") + else: + print(f"文件已提取关键词并保存为: {output_file}") + else: + print(f"未提取到关键词，不创建输出文件 {output_file}。") +# 按类别提取关键词并写入文件 +check_and_write_file('2.txt', 'a0.txt', keywords="央视频道, 8K, 4K, 4k") +check_and_write_file('2.txt', 'a.txt', keywords="央视频道, CCTV") +check_and_write_file('2.txt', 'a1.txt', keywords="央视频道, 第一剧场, 风云剧场, 怀旧剧场, 家庭影院, 高清电影, 影迷, 动作电影, 峨眉电影, 世界地理") + +check_and_write_file('2.txt', 'b0.txt', keywords="卫视频道, 湖北卫视, 湖南卫视, 江苏卫视, 安徽卫视, 凤凰卫视, 辽宁卫视") +check_and_write_file('2.txt', 'b.txt', keywords="卫视频道, 卫视") + +check_and_write_file('2.txt', 'c.txt', keywords="影视频道, 爱情喜剧, 爱喜喜剧, 惊嫊悬疑, 东北热剧, 动作电影, 无名, 都市剧场, iHOT, 海外剧场, 欢笑剧场, 重温经典, 明星大片, 中国功夫, 军旅, 东北热剧, 中国功夫, 军旅剧场, 古装剧场, \ +家庭剧场, 惊悚悬疑, 欢乐剧场, 潮妈辣婆, 爱情喜剧, 精品大剧, 超级影视, 超级电影, 黑莓动画, 黑莓电影, 海外剧场, 精彩影视, 无名影视, 潮婆辣妈, 超级剧, 热播精选") +check_and_write_file('2.txt', 'c1.txt', keywords="影视频道, 求索动物, 求索, 求索科学, 求索记录, 爱谍战, 爱动漫, 爱科幻, 爱青春, 爱自然, 爱科学, 爱浪漫, 爱历史, 爱旅行, 爱奇谈, 爱怀旧, 爱赛车, 爱都市, 爱体育, 爱经典, \ +爱玩具, 爱喜剧, 爱悬疑, 爱幼教, 爱院线") + +check_and_write_file('2.txt', 'e.txt', keywords="港澳频道, TVB, 澳门, 龙华, 民视, 中视, 华视, AXN, MOMO, 采昌, 耀才, 靖天, 镜新闻, 靖洋, 莲花, 年代, 爱尔达, 好莱坞, 华丽, 非凡, 公视, 寰宇, 无线, EVEN, MoMo, 爆谷, 面包, momo, 唐人, \ +中华小, 三立, CNA, FOX, RTHK, Movie, 八大, 中天, 中视, 东森, 凤凰, 天映, 美亚, 环球, 翡翠, 亚洲, 大爱, 大愛, 明珠, 半岛, AMC, 龙祥, 台视, 1905, 纬来, 神话, 经典都市, 视界, 番薯, 私人, 酒店, TVB, 凤凰, 半岛, 星光视界, \ +番薯, 大愛, 新加坡, 星河, 明珠, 环球, 翡翠台, ELTV, 大立, elta, 好消息, 美国中文, 神州, 天良, 18台, BLOOMBERG, Bloomberg, CMUSIC, CN卡通, CNBC, CNBC, CinemaWorld, Cinemax, DMAX, Dbox, Dreamworks, ESPN, Euronews, \ +Eurosports1, FESTIVAL, GOOD2, HBO家庭, HBO, HISTORY, HOY国际财经, HakkaTV, J2, KOREA, LISTENONSPOTIFY, LUXE, MCE, MTV, Now, PremierSports, ROCK, SPOTV, TiTV, VOA, ViuTV, ViuTV6, WSport, WWE, 八度, 博斯, 达文西, 迪士尼, \ +动物星球, 港石金曲, 红牛, 互动英语, 华纳影视, 华语剧台, ELTV, 欢喜台, 旅游, 美食星球, nhkworld, nickjr, 千禧, 全球财经, 探案, 探索, 小尼克, 幸福空间, 影剧, 粤语片台, 智林, 猪哥亮") + +check_and_write_file('2.txt', 'f0.txt', keywords="湖北湖南, 湖北, 湖南") +check_and_write_file('2.txt', 'f.txt', keywords="省市频道, 湖北, 武汉, 松滋, 十堰, 咸宁, 远安, 崇阳, 黄石, 荆州, 当阳, 恩施, 五峰, 来凤, 枝江, 黄冈, 随州, 荆门, 秭归, 宜昌, 长阳, 大悟, 孝感, 鄂州, 垄上, 宜都") +check_and_write_file('2.txt', 'f1.txt', keywords="省市频道, 湖南, 长沙, 常德, 郴州, 垂钓, 金鹰纪实, 衡阳, 怀化, 茶, 吉首, 娄底, 邵阳, 湘潭, 益阳, 永州, 岳阳, 张家界, 株洲, 城步, 崇左, 洪雅, 涟水, 灵石, 隆回, 罗城, 溆浦, 邵阳") + + +#check_and_write_file('2.txt', 'h0.txt', keywords="河南河北, 河南, 河北") +check_and_write_file('2.txt', 'h.txt', keywords="河南河北, 河南, 焦作, 封丘, 郏县, 获嘉, 巩义, 邓州, 宝丰, 开封, 卢氏, 洛阳, 孟津, 安阳, 渑池, 南阳, 林州, 滑县, 栾川, 襄城, 宜阳, 长垣, 内黄, 鹿邑, 新安, 平顶山, 淇县, \ +杞县, 汝阳, 三门峡, 卫辉, 淅川, 新密, 新乡, 信阳, 新郑, 延津, 叶县, 义马, 永城, 禹州, 原阳, 镇平, 郑州, 周口, 泌阳, 郸城, 登封, 扶沟, 潢川, 辉县, 济源, 浚县, 临颍, 灵宝, 鲁山, 罗山, 沁阳, 汝州, 唐河, 尉氏") +check_and_write_file('2.txt', 'h1.txt', keywords="河南河北, 河北, 石家庄, 承德, 丰宁, 临漳, 井陉, 井陉矿区, 保定, 元氏, 兴隆, 内丘, 南宫, 吴桥, 唐县, 唐山, 安平, 定州, 大厂, 张家口, 徐水, 成安, 故城, 康保, 廊坊, 晋州, \ +景县, 武安, 枣强, 柏乡, 涉县, 涞水, 涞源, 涿州, 深州, 深泽, 清河, 秦皇岛, 衡水, 遵化, 邢台, 邯郸, 邱县, 隆化, 雄县, 阜平, 高碑店, 高邑, 魏县, 黄骅, 饶阳, 赵县, 睛彩河北, 滦南, 玉田, 崇礼, 平泉, \ +容城, 文安, 三河, 清河, 潞城, 迁安, 迁西, 清苑, 确山") + + + + + +############################################################################################################################################################################################################################### +##############################################################对生成的文件进行合并 +file_contents = [] +file_paths = ["e.txt", "a0.txt", "a.txt", "a1.txt", "b0.txt", "b.txt", "c.txt", "c1.txt", "c2.txt", "d.txt", "f0.txt", "f.txt", "f1.txt", "g0.txt", "g.txt", "g1.txt", "h0.txt", "h.txt", "h1.txt"] # 替换为实际的文件路径列表 +for file_path in file_paths: + if os.path.exists(file_path): + with open(file_path, 'r', encoding="utf-8") as file: + content = file.read() + file_contents.append(content) + else: # 如果文件不存在，则提示异常并打印提示信息 + print(f"文件 {file_path} 不存在，跳过") +# 写入合并后的文件 +with open("去重.txt", "w", encoding="utf-8") as output: + output.write('\n'.join(file_contents)) + +############################################################################################################################################################################################################################### +##############################################################对生成的文件进行网址及文本去重复，避免同一个频道出现在不同的类中 + +def remove_duplicates(input_file, output_file): + # 用于存储已经遇到的URL和包含genre的行 + seen_urls = set() + seen_lines_with_genre = set() + # 用于存储最终输出的行 + output_lines = [] + # 打开输入文件并读取所有行 + with open(input_file, 'r', encoding='utf-8') as f: + lines = f.readlines() + print("去重前的行数：", len(lines)) + # 遍历每一行 + for line in lines: + # 使用正则表达式查找URL和包含genre的行,默认最后一行 + urls = re.findall(r'[https]?[http]?[P2p]?[mitv]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', line) + genre_line = re.search(r'\bgenre\b', line, re.IGNORECASE) is not None + # 如果找到URL并且该URL尚未被记录 + if urls and urls[0] not in seen_urls: + seen_urls.add(urls[0]) + output_lines.append(line) + # 如果找到包含genre的行，无论是否已被记录，都写入新文件 + if genre_line: + output_lines.append(line) + # 将结果写入输出文件 + with open(output_file, 'w', encoding='utf-8') as f: + f.writelines(output_lines) + print("去重后的行数：", len(output_lines)) +# 使用方法 +remove_duplicates('去重.txt', '分类.txt') + +# 打开文档并读取所有行 +with open('分类.txt', 'r', encoding="utf-8") as file: + lines = file.readlines() +# 使用列表来存储唯一的行的顺序 + unique_lines = [] + seen_lines = set() +# 遍历每一行，如果是新的就加入unique_lines +for line in lines: + if line not in seen_lines: + unique_lines.append(line) + seen_lines.add(line) +# 将唯一的行写入新的文档 +with open('回收站.txt', 'w', encoding="utf-8") as file: + file.writelines(unique_lines) + + + + + +################################################################################################任务结束，删除不必要的过程文件 +files_to_remove = ['去重.txt', "2.txt", "a0.txt", "a.txt", "a1.txt", "b0.txt", "b.txt", "c.txt", "c1.txt", "c2.txt", "d.txt", "e.txt", "f0.txt", "f.txt", "f1.txt", "g0.txt", "g.txt", "g1.txt", "h0.txt", "h.txt", "h1.txt", "i.txt", \ + "i1.txt", "j.txt", "j1.txt", "k.txt", "l0.txt", "l.txt", "l1.txt", "m.txt", "m1.txt", \ + "n0.txt","n.txt","n1.txt", "o1.txt", "o.txt", "p.txt", "汇总.txt"] + +for file in files_to_remove: + if os.path.exists(file): + os.remove(file) + else: # 如果文件不存在，则提示异常并打印提示信息 + print(f"文件 {file} 不存在，跳过删除。") + +print("任务运行完毕，分类频道列表可查看文件夹内综合源.txt文件！")