diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2015-02-19 05:16:11 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2015-02-19 05:16:11 +0100 |
commit | b74d50557757df97c1b2d7a776aa496e623a116c (patch) | |
tree | bfaf269e7a3fd6ec8c19f8f74248043ded90cbc4 | |
parent | e880c66bd800e4769ffdff41fb9dc88cf3206c12 (diff) | |
parent | 9e2d7dca87a15cf455fa6c4843a0241ba0b7ad77 (diff) |
Merge remote-tracking branch 'jbboehr/imgur-gifv-improvements'
-rw-r--r-- | youtube_dl/extractor/imgur.py | 22 |
1 files changed, 17 insertions, 5 deletions
diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index 16488e0c4..7937a5c81 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -5,13 +5,14 @@ import re from .common import InfoExtractor from ..utils import ( int_or_none, + str_or_none, js_to_json, mimetype2ext, + ExtractorError, ) - 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 = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -21,6 +22,14 @@ class ImgurIE(InfoExtractor): '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.', }, + }, { + '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): @@ -34,10 +43,13 @@ class ImgurIE(InfoExtractor): r'<param name="height" value="([0-9]+)"', webpage, 'height', fatal=False)) - formats = [] - video_elements = self._search_regex( + video_elements = str_or_none(self._search_regex( 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 = [] for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements): formats.append({ |