yt-dlp/youtube_dl/extractor/collegehumor.py

74 lines
2.8 KiB
Python
Raw Normal View History

2013-06-23 15:10:21 -04:00
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
ExtractorError,
)
class CollegeHumorIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/(?P<shorttitle>.*)$'
2013-06-23 15:10:21 -04:00
_TEST = {
u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
u'file': u'6902724.mp4',
u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
u'info_dict': {
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.',
},
}
2013-06-23 15:10:21 -04:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group('videoid')
info = {
'id': video_id,
'uploader': None,
'upload_date': None,
}
self.report_extraction(video_id)
xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
metaXml = self._download_webpage(xmlUrl, video_id,
u'Downloading info XML',
u'Unable to download video info XML')
2013-06-23 15:10:21 -04:00
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
videoNode = mdoc.findall('./video')[0]
youtubeIdNode = videoNode.find('./youtubeID')
if youtubeIdNode is not None:
return self.url_result(youtubeIdNode.text, 'Youtube')
2013-06-23 15:10:21 -04:00
info['description'] = videoNode.findall('./description')[0].text
info['title'] = videoNode.findall('./caption')[0].text
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
manifest_url = videoNode.findall('./file')[0].text
except IndexError:
raise ExtractorError(u'Invalid metadata XML file')
manifest_url += '?hdcore=2.10.3'
manifestXml = self._download_webpage(manifest_url, video_id,
u'Downloading XML manifest',
u'Unable to download video info XML')
2013-06-23 15:10:21 -04:00
adoc = xml.etree.ElementTree.fromstring(manifestXml)
try:
media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
node_id = media_node.attrib['url']
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
except IndexError as err:
raise ExtractorError(u'Invalid manifest file')
url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
2013-06-23 15:10:21 -04:00
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
info['ext'] = 'mp4'
2013-06-23 15:10:21 -04:00
return [info]