github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-28 08:00:48 +00:00
Code Issues Projects Releases Packages Wiki Activity

[daum] Support non-numeric video IDs (Fixes #3749)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-09-15 15:25:35 +02:00
parent ca0e7a2b17
commit e5a79071a5
1 changed files with 11 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
youtube_dl/extractor/daum.py
View file

@ -11,10 +11,10 @@
class DaumIE(InfoExtractor): 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' IE_NAME = 'daum.net'
_TEST = { _TESTS = [{
'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690', 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
'info_dict': { 'info_dict': {
'id': '52554690', 'id': '52554690',
@ -24,11 +24,17 @@ class DaumIE(InfoExtractor):
'upload_date': '20130831', 'upload_date': '20130831',
'duration': 3868, '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): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, 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 canonical_url = 'http://tvpot.daum.net/v/%s' % video_id
webpage = self._download_webpage(canonical_url, video_id) webpage = self._download_webpage(canonical_url, video_id)
full_id = self._search_regex( full_id = self._search_regex(
@ -42,7 +48,6 @@ def _real_extract(self, url):
'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query, 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
video_id, 'Downloading video formats info') video_id, 'Downloading video formats info')
self.to_screen(u'%s: Getting video urls' % video_id)
formats = [] formats = []
for format_el in urls.findall('result/output_list/output_list'): for format_el in urls.findall('result/output_list/output_list'):
profile = format_el.attrib['profile'] profile = format_el.attrib['profile']
@ -52,7 +57,7 @@ def _real_extract(self, url):
}) })
url_doc = self._download_xml( url_doc = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, '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 format_url = url_doc.find('result/url').text
formats.append({ formats.append({
'url': format_url, 'url': format_url,