视频爬虫

import osimport ffmpy3import requestsfrom bs4 import BeautifulSoupfrom multiprocessing.dummy import Pool as ThreadPoolarch_keyword = '越狱第一季'arch_url = 'http://www.jisudhw.com/index.php'rach_params = {'m': 'vod-arch'}rach_headers = {    'Ur-Agent':    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36',    'Referer': 'http://www.jisudhw.com/',    'Origin': 'http://www.jisudhw.com',    'Host': 'www.jisudhw.com'}rach_datas = {'wd': arch_keyword, 'submit': 'arch'}video_dir = ''r = requests.post(url=arch_url,                  params=rach_params,                  headers=rach_headers,                  data=rach_datas)r.encoding = 'utf-8'rver = 'http://www.jisudhw.com'arch_html = BeautifulSoup(r.text, 'lxml')arch_spans = arch_html.find_all('span', class_='xing_vb4')for span in arch_spans:    url = rver + span.a.get('href')    name = span.a.string    print(name)    print(url)    video_dir = name    if name not i断桥雪n os.listdir('./'):        os.mkdir(name)    detail_url = url    r = requests.get(url=detail_url)    r.encoding = 'utf-8'    detail_bf = BeautifulSoup(r.text, 'lxml')    num = 1    rach_res = {}    for each_url in detail_bf.find_all('i乌鲁木齐到喀纳斯nput'):        if 'm3u8' in each_url.get('value'):            url = each_url.get('value')            if url not in rach_res.keys():                中山学校rach_res[url] = num            print('第%03d集:' % num)            print(url)            num += 1def downVideo(url):    num = rach_res[url]    name = os.path.join(video_dir, '第%03d集.mp4' % num)    ffmpy3.FFmpeg(executable='D:\\program files\\ffmpeg\\bin\\ffmpeg.exe',                  inputs={                      url: None                  },                  outputs={         实验室制备氯气             name: None                  }).run()# 开8个线程池pool = ThreadPool(8)results = pool.map(downVideo, rach_res.keys())pool.clo()pool.join()

早安爆笑短句运行时效果

视频列表

本文地址：https://blog.csdn.net/m0_37712876/article/details/107655530