diff options
author | felix <m.p.isaev@yandex.com> | 2014-12-12 19:58:44 +0100 |
---|---|---|
committer | felix <m.p.isaev@yandex.com> | 2014-12-12 19:58:44 +0100 |
commit | dc65a213fd73a385470fe1d8f7ad48a174d11bd4 (patch) | |
tree | 3d1a520c5747f84b620e826e09f1f2f50c4e9662 /youtube_dl | |
parent | c3f3b29b92dd46524dcbf9f4b0d957eaa0d0db0c (diff) |
comediansincarsgettingcoffee.com support
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/ccc.py | 46 |
2 files changed, 47 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 447833c01..bd40e9ea5 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -48,6 +48,7 @@ from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .cbs import CBSIE from .cbsnews import CBSNewsIE +from .ccc import ComCarCoffIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py new file mode 100644 index 000000000..809725f12 --- /dev/null +++ b/youtube_dl/extractor/ccc.py @@ -0,0 +1,46 @@ +# encoding: utf-8 +import re +import json + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, +) + +class ComCarCoffIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]+)/?' + _TESTS = [ + { + 'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/', + 'info_dict': { + 'id': 'miranda-sings-happy-thanksgiving-miranda', + 'upload_date': '20141127', + 'title': 'Happy Thanksgiving Miranda', + 'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.', + 'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg', + }, + } + ] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + full_data = json.loads(self._search_regex( + r'<script type="application/json" id="videoData">(?P<json>.+?)</script>', + webpage, 'json')) + + video_id = full_data['activeVideo']['video'] + video_data = full_data['videos'][video_id] + + return { + 'id': video_id, + 'display_id': display_id, + 'title': video_data['title'], + 'description': video_data['description'], + # XXX: the original datum is a full ISO timestamp... why convert it to a worse format? + 'upload_date': unified_strdate(video_data['pubDate']), + 'thumbnail': video_data['images']['thumb'], + # XXX: what do we do with video_data['images']['poster']? + 'formats': self._extract_m3u8_formats(video_data['mediaUrl'], video_id), + } |