From f8e51f60b302357b43ef15cf479da3ce09643f9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Wed, 22 Apr 2015 19:24:14 +0200 Subject: [PATCH] [flickr] Fix extraction (fixes #5501) --- youtube_dl/extractor/flickr.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index 0c858b654..adffe4857 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -3,6 +3,7 @@ import re from .common import InfoExtractor +from ..compat import compat_urllib_request from ..utils import ( ExtractorError, unescapeHTML, @@ -29,9 +30,14 @@ def _real_extract(self, url): video_id = mobj.group('id') video_uploader_id = mobj.group('uploader_id') webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id - webpage = self._download_webpage(webpage_url, video_id) + req = compat_urllib_request.Request(webpage_url) + req.add_header( + 'User-Agent', + # it needs a more recent version + 'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)') + webpage = self._download_webpage(req, video_id) - secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, 'secret') + 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')