import os
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from .youtube import YoutubeIE
ExtractorError,
HEADRequest,
+ parse_xml,
smuggle_url,
unescapeHTML,
unified_strdate,
'info_dict': {
'id': '9ODmcdjQcHQ',
'ext': 'mp4',
+ 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
+ 'upload_date': '20140225',
+ 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
+ 'uploader': 'Tested',
+ 'uploader_id': 'testedcom',
},
# No need to test YoutubeIE here
'params': {
'skip_download': True,
},
},
+ # funnyordie embed
+ {
+ 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
+ 'md5': '7cf780be104d40fea7bae52eed4a470e',
+ 'info_dict': {
+ 'id': '18e820ec3f',
+ 'ext': 'mp4',
+ 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
+ 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
+ }
+ },
+ # nowvideo embed hidden behind percent encoding
+ {
+ 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
+ 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
+ 'info_dict': {
+ 'id': '06e53103ca9aa',
+ 'ext': 'flv',
+ 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
+ 'description': 'No description',
+ },
+ }
]
def report_download_webpage(self, video_id):
# Is it an RSS feed?
try:
- doc = xml.etree.ElementTree.fromstring(webpage.encode('utf-8'))
+ doc = parse_xml(webpage)
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
except compat_xml_parse_error:
pass
+ # Sometimes embedded video player is hidden behind percent encoding
+ # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
+ # Unescaping the whole page allows to handle those cases in a generic way
+ webpage = compat_urllib_parse.unquote(webpage)
+
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
if mobj is not None:
return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
+ # Look for funnyordie embed
+ matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
+ if matches:
+ urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
+ for eurl in matches]
+ return self.playlist_result(
+ urlrs, playlist_id=video_id, playlist_title=video_title)
+
# Start with something easy: JW Player in SWFObject
mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if mobj is None: