def __get_video(self, item_tag): root_index = 'http://www.soku.com' video = Video() video.set_classify_1(self.__video_classify) # 获取title标签 self.__parse_title(video, item_tag) logging.info('视频名称: %s', video.get_name()) if video.get_name() in self.__video_set: logging.info('视频 %s 已经存在', video.get_name()) return None else: self.__video_set.add(video.get_name()) # 获取评分标签 self.__parse_score(video, item_tag) # 获取播放源 self.__parse_source_and_link(video, item_tag) # 获取缩略图 self.__parse_picture_url(video, item_tag) # # 获取剧集标签 self.__parse_drama_num(video, item_tag) # 获取详细链接 detail_link_tag = item_tag.find('li', 'p_link') detail_url = root_index + detail_link_tag.a.attrs.get('href') detail_html = requests.get(detail_url) soup = bs4.BeautifulSoup(detail_html.text, 'html.parser') self.__parse_detail(video, soup) return video