diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-05-10 18:29:36 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-05-10 18:29:36 +0600 |
commit | 3da80389189620408a654c52c36cdd2f5e2c4940 (patch) | |
tree | 60a928a907d44a49c1d2c5cec077ee5c1806d327 /youtube_dl | |
parent | 63cbd19f500eb4d90c1fc7c09f04de5df43a6a04 (diff) | |
parent | a6762c4a22325b5b69770de82df8725d2eb5c3df (diff) |
Merge branch 'duncankl-voicerepublic'
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/voicerepublic.py | 99 |
2 files changed, 100 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 66adb4de7..e808f2734 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -637,6 +637,7 @@ from .vk import ( VKUserVideosIE, ) from .vodlocker import VodlockerIE +from .voicerepublic import VoiceRepublicIE from .vporn import VpornIE from .vrt import VRTIE from .vube import VubeIE diff --git a/youtube_dl/extractor/voicerepublic.py b/youtube_dl/extractor/voicerepublic.py new file mode 100644 index 000000000..1106c655b --- /dev/null +++ b/youtube_dl/extractor/voicerepublic.py @@ -0,0 +1,99 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + determine_ext, + int_or_none, +) + + +class VoiceRepublicIE(InfoExtractor): + _VALID_URL = r'https?://voicerepublic\.com/(?:talks|embed)/(?P<id>[0-9a-z-]+)' + _TESTS = [{ + 'url': 'http://voicerepublic.com/talks/watching-the-watchers-building-a-sousveillance-state', + 'md5': '0554a24d1657915aa8e8f84e15dc9353', + 'info_dict': { + 'id': '2296', + 'display_id': 'watching-the-watchers-building-a-sousveillance-state', + 'ext': 'm4a', + 'title': 'Watching the Watchers: Building a Sousveillance State', + 'description': 'md5:715ba964958afa2398df615809cfecb1', + 'thumbnail': 're:^https?://.*\.(?:png|jpg)$', + 'duration': 1800, + 'view_count': int, + } + }, { + 'url': 'http://voicerepublic.com/embed/watching-the-watchers-building-a-sousveillance-state', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + req = compat_urllib_request.Request( + compat_urlparse.urljoin(url, '/talks/%s' % display_id)) + # Older versions of Firefox get redirected to an "upgrade browser" page + req.add_header('User-Agent', 'youtube-dl') + webpage = self._download_webpage(req, display_id) + + if '>Queued for processing, please stand by...<' in webpage: + raise ExtractorError( + 'Audio is still queued for processing', expected=True) + + data = self._parse_json( + self._search_regex( + r'(?s)return ({.+?});\s*\n', webpage, + 'data', default=None), + display_id, fatal=False) + + if data: + title = data['title'] + description = data.get('teaser') + talk_id = data.get('talk_id') or display_id + talk = data['talk'] + duration = int_or_none(talk.get('duration')) + formats = [{ + 'url': compat_urlparse.urljoin(url, talk_url), + 'format_id': format_id, + 'ext': determine_ext(talk_url) or format_id, + 'vcodec': 'none', + } for format_id, talk_url in talk['links'].items()] + else: + title = self._og_search_title(webpage) + description = self._html_search_regex( + r"(?s)<div class='talk-teaser'[^>]*>(.+?)</div>", + webpage, 'description', fatal=False) + talk_id = self._search_regex( + [r"id='jc-(\d+)'", r"data-shareable-id='(\d+)'"], + webpage, 'talk id', default=None) or display_id + duration = None + formats = [{ + 'url': compat_urlparse.urljoin(url, talk_url), + 'format_id': format_id, + 'ext': determine_ext(talk_url) or format_id, + 'vcodec': 'none', + } for format_id, talk_url in re.findall(r"data-([^=]+)='([^']+)'", webpage)] + self._sort_formats(formats) + + thumbnail = self._og_search_thumbnail(webpage) + view_count = int_or_none(self._search_regex( + r"class='play-count[^']*'>\s*(\d+) plays", + webpage, 'play count', fatal=False)) + + return { + 'id': talk_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + } |