According to the rules of regular crawling a site's video (not debugging, to be modified)

Requests Import 
Import module Re # regular 
import uuid # uuid.uuid (4) can be generated in a period of the world's only random string based on timestamp 


# trilogy crawler 
1, a transmission request # 
# 2, parses the data 
# 3, data stored 
# and write the following one by a function package to achieve code reuse 
# 1, sends a request 

DEF the get_page (URL): 
    Response = requests.get (URL) 
    return Response 


# 2, analysis data 
# acquires video before parsing Home page ID 
DEF parse_index (text) : 
    RES = re.findall ( '.? <A href = "Video _ (*)', response.text, re.S) 
    #Print (RES) 
    detail_url_list = [] 
    for m_id in RES: 
        detail_url = 'HTTPS: // www.pearvideo.com/video_'+m_id 
        detail_url_list.append (detail_url) 
    return detail_url_list 


## to resolve the details page for the video url 
DEF parse_detail (text):
    "" " 
  Find a web developer tools tags: 
  <Video WebKit-playsinline =" "playsinline =" "the X--WebKit-AirPlay =" "autoplay =" autoplay " 
  src =" https://video.pearvideo.com/ MP4 / adshort / 20,190,613 / 1566073-14015522_adpkg-CONT-ad_hd.mp4 "S 
  tylE =" width: 100%; height: 100%; "> </ Video> 

<Video the src * =?" "(*.?) 

    # = re.findall movie_url (( '<* Video? src = "(. *?)"', text, re.S)) 

    # js but found that the rule is a secondary packaging, they need to revise the rules of regular 

    # modifications regular 
    "" " 
    " "" 
    open source details page, and then ctrl + F to find src_Url 

    <Script of the type = "text / JavaScript"> 
    var 
    contID = "1,566,073", liveStatusUrl = "liveStatus.jsp", liveSta = "", playSta = "1", 
    autoPlay =!1, isLiving =!1, isVrVideo =!1, hdflvUrl = "", sdflvUrl = "", hdUrl = "", sdUrl = "", ldUrl = "", \
                                                                                                            
      srcUrl = "https://video.pearvideo.com/mp4/adshort/20190613/cont-1566073-14015522_adpkg-ad_hd.mp4",\
    vdoUrl = srcUrl, skinRes = "//www.pearvideo.com/domain/skin", videoCDN = "//video.pearvideo.com";
    
    推出正则表达式：
 srcUrl ="(.*?)" 
          """

    movie_url = re.findall(('srcUrl ="(.*?)" ', text, re.S))
    return movie_url


#3、保存数据

def save_movie(movie_url):
    response = requests.get(movie_url)
#把视频写到本地
    with open(f'{uuid.uuid4()}.mp4', 'wb') as f:# test: call the function and achieve crawling        f.flush ()
        f.write (response.content)





__name__ __ == IF '__ main__': 
    #. 1, a transmission request for Home 
    index_res the get_page = Response = (URL = 'HTTPS: //www.pearvideo.com/') 
    # 2, on the home page is parsed for details page 
    detail_url_list = parse_index (index_res.text) 
    Print (detail_url_list) 
    # 3. for more details, send a request for each page URL 
    for detail_url in detail_url_list: 
        detail_res the get_page = (URL = detail_url) 
        #Print (detail_res.text) 

       # R & lt climbed above the plurality of pages 70 

    # 4. resolve details page for the video url 
    movie_url = parse_detail (detail_res.text) 
    Print (movie_url) 

    # 5, save the video to a local 

    save_movie (movie_url)