youtube.py 文件源码

def extract_videos_from_page(self, page):
        ids_in_page = []
        titles_in_page = []
        for mobj in re.finditer(self._VIDEO_RE, page):
            # The link with index 0 is not the first video of the playlist (not sure if still actual)
            if 'index' in mobj.groupdict() and mobj.group('id') == '0':
                continue
            video_id = mobj.group('id')
            video_title = unescapeHTML(mobj.group('title'))
            if video_title:
                video_title = video_title.strip()
            try:
                idx = ids_in_page.index(video_id)
                if video_title and not titles_in_page[idx]:
                    titles_in_page[idx] = video_title
            except ValueError:
                ids_in_page.append(video_id)
                titles_in_page.append(video_title)
        return zip(ids_in_page, titles_in_page)