diff options
author | Philipp Hagemeister <[email protected]> | 2015-01-04 03:15:27 +0100 |
---|---|---|
committer | Philipp Hagemeister <[email protected]> | 2015-01-04 03:15:27 +0100 |
commit | 7a1818c99b1729796f62c341b1b3f809cd47dbf8 (patch) | |
tree | e44bd29d7443bbe3139d91dfa6a88d5bde2aafff | |
parent | 2ccd1b10e58cc8e5173dc1aeedc2b3f0ef9b55bf (diff) | |
download | youtube-dl-7a1818c99b1729796f62c341b1b3f809cd47dbf8.tar.gz youtube-dl-7a1818c99b1729796f62c341b1b3f809cd47dbf8.zip |
[vk] Add support for rutube embeds (Fixes #4514)
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/rutube.py | 31 | ||||
-rw-r--r-- | youtube_dl/extractor/vk.py | 9 |
3 files changed, 41 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index c3dc09f75..143cd5c49 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -359,6 +359,7 @@ from .ruhd import RUHDIE from .rutube import ( RutubeIE, RutubeChannelIE, + RutubeEmbedIE, RutubeMovieIE, RutubePersonIE, ) diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py index b72b5a586..5b1c3577a 100644 --- a/youtube_dl/extractor/rutube.py +++ b/youtube_dl/extractor/rutube.py @@ -70,6 +70,37 @@ class RutubeIE(InfoExtractor): } +class RutubeEmbedIE(InfoExtractor): + IE_NAME = 'rutube:embed' + IE_DESC = 'Rutube embedded videos' + _VALID_URL = 'https?://rutube\.ru/video/embed/(?P<id>[0-9]+)' + + _TEST = { + 'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=', + 'info_dict': { + 'id': 'a10e53b86e8f349080f718582ce4c661', + 'ext': 'mp4', + 'upload_date': '20131223', + 'uploader_id': '297833', + 'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89', + 'uploader': 'subziro89 ILya', + 'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89', + }, + 'params': { + 'skip_download': 'Requires ffmpeg', + }, + } + + def _real_extract(self, url): + embed_id = self._match_id(url) + webpage = self._download_webpage(url, embed_id) + + canonical_url = self._html_search_regex( + r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage, + 'Canonical URL') + return self.url_result(canonical_url, 'Rutube') + + class RutubeChannelIE(InfoExtractor): IE_NAME = 'rutube:channel' IE_DESC = 'Rutube channels' diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 542e9198a..129de6cf3 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -164,6 +164,15 @@ class VKIE(InfoExtractor): self.to_screen('Youtube video detected') return self.url_result(m_yt.group(1), 'Youtube') + m_rutube = re.search( + r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) + assert m_rutube + if m_rutube is not None: + self.to_screen('rutube video detected') + rutube_url = self._proto_relative_url( + m_rutube.group(1).replace('\\', '')) + return self.url_result(rutube_url) + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page) if m_opts: m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1)) |