From 5ace137bf4af2dda4ee17e72716d78783700b07d Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Mon, 24 Oct 2016 15:13:17 +0800 Subject: [PATCH] [dotsub] Support vimeo embed (closes #10964) --- ChangeLog | 1 + youtube_dl/extractor/dotsub.py | 46 ++++++++++++++++++++++++++++------ 2 files changed, 39 insertions(+), 8 deletions(-) diff --git a/ChangeLog b/ChangeLog index 7dabde861..f64dcbc48 100644 --- a/ChangeLog +++ b/ChangeLog @@ -4,6 +4,7 @@ Core * Running youtube-dl in the background is fixed (#10996, #10706, #955) Extractors ++ [dotsub] Support Vimeo embed (#10964) * [litv] Fix extraction diff --git a/youtube_dl/extractor/dotsub.py b/youtube_dl/extractor/dotsub.py index fd64d1a7f..1f75352ca 100644 --- a/youtube_dl/extractor/dotsub.py +++ b/youtube_dl/extractor/dotsub.py @@ -9,7 +9,7 @@ class DotsubIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P[^/]+)' - _TEST = { + _TESTS = [{ 'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09', 'md5': '21c7ff600f545358134fea762a6d42b6', 'info_dict': { @@ -24,7 +24,24 @@ class DotsubIE(InfoExtractor): '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 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( [r']+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(?!\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 @@ def _real_extract(self, url): 'uploader': info.get('user'), 'timestamp': float_or_none(info.get('dateCreated'), 1000), 'view_count': int_or_none(info.get('numberOfViews')), - } + }) + + return info_dict