python抓取微博用户发布的视频

最近抽空写了数据抓取微博用户发布在奉天承芸超话的视频，代码运行通过，抓取代码如下：

后续出个去掉抓取重复网页的优化版本，等我稍闲下来。

def run(self):
    s = requests.Session()
#暂时先抓self.TotalPage=200页
    for i in range(1,self.TotalPage):
        time.sleep(1)
        if self.end_flag :
            break
        if i == 1:
            self.url = self.basic_weibo_url
        else:
            self.url = self.basic_weibo_url + '&since_id=' + str(self.since_id)

        weibo_response = s.get(self.url,timeout=(3.15,10))
        weibo_data = weibo_response.json()
        if weibo_response.status_code != 200:
            print("end process for reponse.status_code=", weibo_response.status_code)
            self.end_flag = True
            return self.end_flag
        if weibo_data['data'].get('cards'):
            cards = weibo_data['data']['cards']
            if weibo_data['data'].get('cardlistInfo'):
                cardlistInfo = weibo_data['data']['cardlistInfo']
                self.since_id = cardlistInfo.get('since_id')
                if self.since_id == '':
                    print("end process for since_id is empty")
                    self.end_flag = True
                    return self.end_flag
                for card in cards:
                    if card.get('mblog'):
                        m_blog = card.get('mblog')
                        text = m_blog.get('text')
                        mid = m_blog.get('mid')
                        source = m_blog.get('source')
                        screen_name = m_blog.get('user').get('screen_name')
                        # created_at = ''
                        # edit_at = ''
                        created_at = m_blog.get('created_at')
                        edit_at = m_blog.get('edit_at')
                        #发布在奉天承芸超话里面
                        if source == self.weibo_str:
                            # print([mid,text,screen_name])
                            if m_blog.get('page_info'):
                                page_info = m_blog.get('page_info')
                                # content2 = ''
                                content2 = page_info.get('content2')
                                type = page_info.get('type')
                                if page_info.get('type') == "video":
                                    page_url = page_info.get('page_url')
                                    # play_count = ''
                                    play_count = page_info.get('play_count')
                                    page_title = page_info.get('title')
                                    self.item_num = self.item_num + 1
                                    if page_info.get('page_pic'):
                                        video_pic_url = ''
                                        page_pic = page_info.get('page_pic')
                                        video_pic_url = page_pic['url']
                                        # print(video_pic_url)
                                    print("append")
                                    ws1.append(
                                        [str(self.item_num), page_title, screen_name, content2, "1-视频", "3-双人合作舞台-饭拍",
                                         "2-微博", page_url, video_pic_url, created_at, play_count, '', ''])

                wb.save('media.xlsx')
            else:
                print("end process for there is not cardlistInfo")
                self.end_flag = True
                return self.end_flag