From: Jaime Marquínez Ferrándiz Date: Wed, 22 Apr 2015 17:58:39 +0000 (+0200) Subject: [flickr] Don't use regex for extracting the info from the xml files X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=c04c3e334cc7ff0bbd2cbb8167f5cd2794c29d29;p=youtube-dl [flickr] Don't use regex for extracting the info from the xml files --- diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index adffe4857..2fe76d661 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -6,7 +6,7 @@ from .common import InfoExtractor from ..compat import compat_urllib_request from ..utils import ( ExtractorError, - unescapeHTML, + find_xpath_attr, ) @@ -40,20 +40,21 @@ class FlickrIE(InfoExtractor): secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret') first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self' - first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage') + first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage') - node_id = self._html_search_regex(r'(\d+-\d+)', - first_xml, 'node_id') + node_id = find_xpath_attr( + first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id', + 'id').text second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' - second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage') + second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage') self.report_extraction(video_id) - mobj = re.search(r'