[dotsub] Support vimeo embed (closes #10964)

This commit is contained in:
Yen Chi Hsuan 2016-10-24 15:13:17 +08:00
parent 9dde0e04e6
commit 5ace137bf4
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
2 changed files with 39 additions and 8 deletions

View File

@ -4,6 +4,7 @@ Core
* Running youtube-dl in the background is fixed (#10996, #10706, #955) * Running youtube-dl in the background is fixed (#10996, #10706, #955)
Extractors Extractors
+ [dotsub] Support Vimeo embed (#10964)
* [litv] Fix extraction * [litv] Fix extraction

View File

@ -9,7 +9,7 @@
class DotsubIE(InfoExtractor): class DotsubIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)' _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
_TEST = { _TESTS = [{
'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09', 'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
'md5': '21c7ff600f545358134fea762a6d42b6', 'md5': '21c7ff600f545358134fea762a6d42b6',
'info_dict': { 'info_dict': {
@ -24,7 +24,24 @@ class DotsubIE(InfoExtractor):
'upload_date': '20131130', 'upload_date': '20131130',
'view_count': int, 'view_count': int,
} }
} }, {
'url': 'https://dotsub.com/view/747bcf58-bd59-45b7-8c8c-ac312d084ee6',
'md5': '2bb4a83896434d5c26be868c609429a3',
'info_dict': {
'id': '168006778',
'ext': 'mp4',
'title': 'Apartments and flats in Raipur the white symphony',
'description': 'md5:784d0639e6b7d1bc29530878508e38fe',
'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
'duration': 290,
'timestamp': 1476767794.2809999,
'upload_date': '20160525',
'uploader': 'parthivi001',
'uploader_id': 'user52596202',
'view_count': int,
},
'add_ie': ['Vimeo'],
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -37,12 +54,23 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._search_regex( video_url = self._search_regex(
[r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'], [r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
webpage, 'video url') webpage, 'video url', default=None)
info_dict = {
'id': video_id,
'url': video_url,
'ext': 'flv',
}
return { if not video_url:
'id': video_id, setup_data = self._parse_json(self._html_search_regex(
'url': video_url, r'(?s)data-setup=([\'"])(?P<content>(?!\1).+?)\1',
'ext': 'flv', webpage, 'setup data', group='content'), video_id)
info_dict = {
'_type': 'url_transparent',
'url': setup_data['src'],
}
info_dict.update({
'title': info['title'], 'title': info['title'],
'description': info.get('description'), 'description': info.get('description'),
'thumbnail': info.get('screenshotURI'), 'thumbnail': info.get('screenshotURI'),
@ -50,4 +78,6 @@ def _real_extract(self, url):
'uploader': info.get('user'), 'uploader': info.get('user'),
'timestamp': float_or_none(info.get('dateCreated'), 1000), 'timestamp': float_or_none(info.get('dateCreated'), 1000),
'view_count': int_or_none(info.get('numberOfViews')), 'view_count': int_or_none(info.get('numberOfViews')),
} })
return info_dict