Python爬取新浪微博博主高清视频

#! -*- coding:utf-8 -*-
import urllib2,urllib,json,datetime,datetime,time,requests,re


#获取uid,url
def getUrl(name):
    #主页
    Surl = 'https://m.weibo.cn/api/container/getIndex?containerid=100103type%3D1%26q%3D'+urllib.quote(name)+'&page_type=searchall'
    print '主页:',Surl
    req = urllib2.Request(Surl,None,headers)
    res = json.loads(urllib2.urlopen(req).read())
    lfid = res['data']['scheme'].split('lfid=')[1].split('_-_')[0]
    # print res['data']['scheme']
    uid = res['data']['cards'][0]['card_group'][0]['user']['id']
    profile_url = res['data']['cards'][0]['card_group'][0]['user']['profile_url']
    back = profile_url.split('&luicode=')[1]
    print '获取uid',uid,profile_url,back
    url2 = 'https://m.weibo.cn/api/container/getIndex?uid={0}&luicode={1}&type=uid&value={2}'.format(uid,back,uid)
    print url2
    containerid = getContained(url2)

    print '*'*100
    print containerid
    for i in range(100):
        videoList = 'https://m.weibo.cn/api/container/getIndex?uid={0}&luicode={1}&type=uid&value={2}&containerid={3}_-_mcn_time'.format(uid, back, uid, containerid)
        print '-' * 100
        print videoList+'&page='+str(i)
        bool = getInfo(videoList+'&page='+str(i))
        if bool == True:
            break
#获取containedid
def getContained(url):
    req = urllib2.Request(url, None, headers)
    res = json.loads(urllib2.urlopen(req).read())
    container = res['data']['tabsInfo']['tabs'][2]['containerid']
    return container


def getInfo(url):

    headers={
        'User-Agent':'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1',
        'X-DevTools-Emulate-Network-Conditions-Client-Id': '81ED134A01BAFB218319255E8C4C958E',
        'Referer': 'https://m.weibo.cn/u/1912713353?uid=1912713353&luicode=10000011&lfid=100103type%3D1%26q%3D6%E5%B2%9B%E5%B2%9B'
    }

    req = urllib2.Request(url,None,headers)
    res = urllib2.urlopen(req).read()
    if len(res) < 100:
        return True

    mediaList = json.loads(res)['data']['cards']
    # print mediaList
    for m in mediaList:
        item = dict()
    
        
        create_time = datetime.datetime.now()
        source = m['mblog']['page_info']['page_url']
        object_id = m['mblog']['page_info']['object_id']

        title = m['mblog']['page_info']['content2']
        # videosRoute = m['mblog']['page_info']['media_info']['stream_url']
        img = m['mblog']['page_info']['page_pic']['url']
        author = m['mblog']['user']['screen_name']
        support = m['mblog']['attitudes_count']
        info = m['mblog']['page_info']['content2']
        #11111111111111111111111
        try:
            print source,object_id
            url_source = 'http://video.weibo.com/show?fid='+object_id
            html = requests.get(url_source, headers=headers1, allow_redirects=False)
            url2 = html.headers['Location']
            reqw = urllib2.Request(url2, None, headers2)
            resw = urllib2.urlopen(reqw).read()
            vs = re.compile(r'video-sources="(.*?)"', re.S)
            v = re.findall(vs, resw)[0]
            str1 = urllib.unquote(v)
            str2 = str1.split('http://')[-1]
            videosRoute = 'http://' + str2
            print '^'*100
            print videosRoute
        except IndexError:
            print 'eeeeeeeeeeeeeeee'
            videosRoute = m['mblog']['page_info']['media_info']['stream_url']
        #111111111111111111111111
        item['title'] = title
        item['author'] = author
        item['video_url'] = videosRoute
        item['img_route'] = img
        item['support'] = support
        item['description'] = info
        item['create_time'] = create_time

        try:
            item['video_name'] = videosRoute.split('cn/')[1].split('?')[0]
            item['img_name'] = img.split('cn/')[1].split('?')[0]
        except IndexError:
            item['video_name'] = videosRoute.split('stream/')[1].split('?')[0]
            try:
                item['img_name'] = img.split('images/')[1]
            except IndexError:
                item['img_name'] = img.split('stream/')[1]
            print img
        item['video_route'] = 'http://video.xxxx.com/' + item['video_name']
        item['video_img'] = 'http://video.xxxx.com/' + item['img_name']
        item['tag0'] = ""
        print 'title',title
        print '视频url',videosRoute
        print '视频img',img
        print '视频作者',author
        print '点赞数',support

        print '内容',info
        print '-'*100



name = '李子柒'
getUrl(name)