Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-19 09:25:43 +00:00
Code Issues Projects Releases Wiki Activity

[collegehumor] Allow old-style videos (Fixes #1285)

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-08-21 03:50:56 +02:00
parent d741e55a42
commit 87f78946a5
1 changed files with 33 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
youtube_dl/extractor/collegehumor.py
View File

@ -4,6 +4,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
determine_ext,
ExtractorError, ExtractorError,
) )
@ -12,7 +13,7 @@
class CollegeHumorIE(InfoExtractor): class CollegeHumorIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$' _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
_TEST = { _TESTS = [{
u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe', u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
u'file': u'6902724.mp4', u'file': u'6902724.mp4',
u'md5': u'1264c12ad95dca142a9f0bf7968105a0', u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
@ -20,7 +21,16 @@ class CollegeHumorIE(InfoExtractor):
u'title': u'Comic-Con Cosplay Catastrophe', u'title': u'Comic-Con Cosplay Catastrophe',
u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.', u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.',
}, },
} },
{
u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
u'file': u'3505939.mp4',
u'md5': u'c51ca16b82bb456a4397987791a835f5',
u'info_dict': {
u'title': u'Font Conference',
u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
},
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -49,25 +59,29 @@ def _real_extract(self, url):
info['description'] = videoNode.findall('./description')[0].text info['description'] = videoNode.findall('./description')[0].text
info['title'] = videoNode.findall('./caption')[0].text info['title'] = videoNode.findall('./caption')[0].text
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
manifest_url = videoNode.findall('./file')[0].text next_url = videoNode.findall('./file')[0].text
except IndexError: except IndexError:
raise ExtractorError(u'Invalid metadata XML file') raise ExtractorError(u'Invalid metadata XML file')
manifest_url += '?hdcore=2.10.3' if next_url.endswith(u'manifest.f4m'):
manifestXml = self._download_webpage(manifest_url, video_id, manifest_url = next_url + '?hdcore=2.10.3'
u'Downloading XML manifest', manifestXml = self._download_webpage(manifest_url, video_id,
u'Unable to download video info XML') u'Downloading XML manifest',
u'Unable to download video info XML')
adoc = xml.etree.ElementTree.fromstring(manifestXml) adoc = xml.etree.ElementTree.fromstring(manifestXml)
try: try:
media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0] media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
node_id = media_node.attrib['url'] node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError as err: except IndexError as err:
raise ExtractorError(u'Invalid manifest file') raise ExtractorError(u'Invalid manifest file')
url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
info['ext'] = 'mp4'
else:
# Old-style direct links
info['url'] = next_url
info['ext'] = determine_ext(info['url'])
url_pr = compat_urllib_parse_urlparse(info['thumbnail']) return info
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
info['ext'] = 'mp4'
return [info]