w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[flickr] Fix extraction (fixes #5501)

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2015-04-22 19:24:14 +02:00
parent 33b066bda0
commit f8e51f60b3
1 changed files with 8 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
youtube_dl/extractor/flickr.py
View file

@ -3,6 +3,7 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
unescapeHTML, unescapeHTML,
@ -29,9 +30,14 @@ class FlickrIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
video_uploader_id = mobj.group('uploader_id') video_uploader_id = mobj.group('uploader_id')
webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_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_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_webpage(first_url, video_id, 'Downloading first data webpage')