aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/dotsub.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/dotsub.py')
-rw-r--r--youtube_dl/extractor/dotsub.py66
1 files changed, 48 insertions, 18 deletions
diff --git a/youtube_dl/extractor/dotsub.py b/youtube_dl/extractor/dotsub.py
index e9ca236d4..1f75352ca 100644
--- a/youtube_dl/extractor/dotsub.py
+++ b/youtube_dl/extractor/dotsub.py
@@ -9,22 +9,39 @@ from ..utils import (
class DotsubIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
- _TEST = {
- 'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
- 'md5': '0914d4d69605090f623b7ac329fea66e',
+ _TESTS = [{
+ 'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
+ 'md5': '21c7ff600f545358134fea762a6d42b6',
'info_dict': {
- 'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+ 'id': '9c63db2a-fa95-4838-8e6e-13deafe47f09',
'ext': 'flv',
- 'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
- 'description': 'md5:699a0f7f50aeec6042cb3b1db2d0d074',
- 'thumbnail': 're:^https?://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
- 'duration': 3169,
- 'uploader': '4v4l0n42',
- 'timestamp': 1292248482.625,
- 'upload_date': '20101213',
+ 'title': 'MOTIVATION - "It\'s Possible" Best Inspirational Video Ever',
+ 'description': 'md5:41af1e273edbbdfe4e216a78b9d34ac6',
+ 'thumbnail': 're:^https?://dotsub.com/media/9c63db2a-fa95-4838-8e6e-13deafe47f09/p',
+ 'duration': 198,
+ 'uploader': 'liuxt',
+ 'timestamp': 1385778501.104,
+ 'upload_date': '20131130',
'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):
video_id = self._match_id(url)
@@ -37,12 +54,23 @@ class DotsubIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
[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 {
- 'id': video_id,
- 'url': video_url,
- 'ext': 'flv',
+ if not video_url:
+ setup_data = self._parse_json(self._html_search_regex(
+ r'(?s)data-setup=([\'"])(?P<content>(?!\1).+?)\1',
+ webpage, 'setup data', group='content'), video_id)
+ info_dict = {
+ '_type': 'url_transparent',
+ 'url': setup_data['src'],
+ }
+
+ info_dict.update({
'title': info['title'],
'description': info.get('description'),
'thumbnail': info.get('screenshotURI'),
@@ -50,4 +78,6 @@ class DotsubIE(InfoExtractor):
'uploader': info.get('user'),
'timestamp': float_or_none(info.get('dateCreated'), 1000),
'view_count': int_or_none(info.get('numberOfViews')),
- }
+ })
+
+ return info_dict