【爬虫】爬取a站目标列表视频

name)if __name__ == '__main__':url = https://www.acfun.cn/v/list135/index.htm?sortField=rankScoreduration=alldate=defaultpage=1main(url) ， ''， headers=headers)info = re.findall('window.pageInfo = window.videoInfo = (.*?)window.videoResource ='， r.text， class_=list-content-item)links_list = []for link in links:url = https://www.acfun.cn + link.a.get('href')links_list.append(url)return links_listdef main(urll):index_url = urlllinks = get_index_links(index_url)for url in links:m3u8_url， headers=headers)ts_files = re.sub('#.*'， name = get_m3u8_list(url)ts_files = get_ts_files(m3u8_url)download_combine(ts_files。

'ab') as f:for ts in tqdm(ts_files):url = 'https://tx-safety-video.acfun.cn/mediacloud/acfun/acfun_video/' + tscontent = requests.get(url。

like Gecko) Chrome/127.0.0.0 Safari/537.36'}# 获取m3u8列表文件def get_m3u8_list(url):r = requests.get(url， （仅做学习，如有侵权，name)return info_json， headers=headers).contentf.write(content)f.close()# 获取目录页的视频链接def get_index_links(index_url):r = requests.get(index_url， re.S)[0].strip()[:-1]info_json = \json.loads(json.loads(info)[currentVideoInfo][ksPlayJsonHevc])['adaptationSet'][0]['representation'][0]['url']# pprint.pprint(info_json)name = json.loads(info)[title]name = re.sub(r'[|?/\\]'，''， headers=headers)soup = BeautifulSoup(r.text， name):path = os.getcwd()with open(f'{path}/{name}.mp4'，请私信） [Python] 纯文本查看 复制代码 import osimport pprintimport reimport jsonimport requestsimport fake_useragentfrom tqdm import tqdm # 显示进度条from bs4 import BeautifulSoupua = fake_useragent.UserAgent().randomheaders = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML， r.text).split()return ts_files# 下载并合并视频片段def download_combine(ts_files， name# 提取所有视频片段的播放地址 ts文件def get_ts_files(url):r = requests.get(url， 'html.parser')links = soup.find_all('div'，。