diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2014-09-15 15:25:35 +0200 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2014-09-15 15:25:35 +0200 |
| commit | e5a79071a5023940fb0c39d3b04f8cc6a913dfee (patch) | |
| tree | 73ffc8eb341f5a1368151d28989f7bd4991a3f28 | |
| parent | ca0e7a2b17387c552c41afe705016b98d6677f51 (diff) | |
| download | youtube-dl-e5a79071a5023940fb0c39d3b04f8cc6a913dfee.tar.gz youtube-dl-e5a79071a5023940fb0c39d3b04f8cc6a913dfee.tar.xz youtube-dl-e5a79071a5023940fb0c39d3b04f8cc6a913dfee.zip | |
[daum] Support non-numeric video IDs (Fixes #3749)
| -rw-r--r-- | youtube_dl/extractor/daum.py | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 6033cd94a..45d66e2e6 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -11,10 +11,10 @@ from ..utils import ( class DaumIE(InfoExtractor): - _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)' + _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)' IE_NAME = 'daum.net' - _TEST = { + _TESTS = [{ 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', 'info_dict': { 'id': '52554690', @@ -24,11 +24,17 @@ class DaumIE(InfoExtractor): 'upload_date': '20130831', 'duration': 3868, }, - } + }, { + 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz', + 'only_matching': True, + }, { + 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = mobj.group('id') canonical_url = 'http://tvpot.daum.net/v/%s' % video_id webpage = self._download_webpage(canonical_url, video_id) full_id = self._search_regex( @@ -42,7 +48,6 @@ class DaumIE(InfoExtractor): 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query, video_id, 'Downloading video formats info') - self.to_screen(u'%s: Getting video urls' % video_id) formats = [] for format_el in urls.findall('result/output_list/output_list'): profile = format_el.attrib['profile'] @@ -52,7 +57,7 @@ class DaumIE(InfoExtractor): }) url_doc = self._download_xml( 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, - video_id, note=False) + video_id, note='Downloading video data for %s format' % profile) format_url = url_doc.find('result/url').text formats.append({ 'url': format_url, |