dailymotion.py 文件源码

def _extract_entries(self, id):
        video_ids = set()
        processed_urls = set()
        for pagenum in itertools.count(1):
            page_url = self._PAGE_TEMPLATE % (id, pagenum)
            webpage, urlh = self._download_webpage_handle_no_ff(
                page_url, id, 'Downloading page %s' % pagenum)
            if urlh.geturl() in processed_urls:
                self.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
                    page_url, urlh.geturl()), id)
                break

            processed_urls.add(urlh.geturl())

            for video_id in re.findall(r'data-xid="(.+?)"', webpage):
                if video_id not in video_ids:
                    yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
                    video_ids.add(video_id)

            if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                break