Merge remote-tracking branch 'jbboehr/imgur-gifv-improvements'

This commit is contained in:
Philipp Hagemeister 2015-02-19 05:16:11 +01:00
commit b74d505577

View File

@ -5,13 +5,14 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
str_or_none,
js_to_json, js_to_json,
mimetype2ext, mimetype2ext,
ExtractorError,
) )
class ImgurIE(InfoExtractor): class ImgurIE(InfoExtractor):
_VALID_URL = r'https?://i\.imgur\.com/(?P<id>[a-zA-Z0-9]+)\.(?:mp4|gifv)' _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)(?:\.mp4|\.gifv)?'
_TESTS = [{ _TESTS = [{
'url': 'https://i.imgur.com/A61SaA1.gifv', 'url': 'https://i.imgur.com/A61SaA1.gifv',
@ -21,6 +22,14 @@ class ImgurIE(InfoExtractor):
'title': 'MRW gifv is up and running without any bugs', 'title': 'MRW gifv is up and running without any bugs',
'description': 'The Internet\'s visual storytelling community. Explore, share, and discuss the best visual stories the Internet has to offer.', 'description': 'The Internet\'s visual storytelling community. Explore, share, and discuss the best visual stories the Internet has to offer.',
}, },
}, {
'url': 'https://imgur.com/A61SaA1',
'info_dict': {
'id': 'A61SaA1',
'ext': 'mp4',
'title': 'MRW gifv is up and running without any bugs',
'description': 'The Internet\'s visual storytelling community. Explore, share, and discuss the best visual stories the Internet has to offer.',
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -34,10 +43,13 @@ def _real_extract(self, url):
r'<param name="height" value="([0-9]+)"', r'<param name="height" value="([0-9]+)"',
webpage, 'height', fatal=False)) webpage, 'height', fatal=False))
formats = [] video_elements = str_or_none(self._search_regex(
video_elements = self._search_regex(
r'(?s)<div class="video-elements">(.*?)</div>', r'(?s)<div class="video-elements">(.*?)</div>',
webpage, 'video elements') webpage, 'video elements', fatal=False))
if not video_elements:
raise ExtractorError(
'No sources found for video %s' % video_id, expected=True)
formats = [] formats = []
for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements): for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements):
formats.append({ formats.append({