diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/ccc.py | 46 | ||||
| -rw-r--r-- | youtube_dl/extractor/comcarcoff.py | 52 |
3 files changed, 53 insertions, 47 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index bd40e9ea5..119ec2044 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -48,7 +48,6 @@ 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 @@ -66,6 +65,7 @@ from .cnn import ( ) from .collegehumor import CollegeHumorIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE +from .comcarcoff import ComCarCoffIE from .condenast import CondeNastIE from .cracked import CrackedIE from .criterion import CriterionIE diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py deleted file mode 100644 index 809725f12..000000000 --- a/youtube_dl/extractor/ccc.py +++ /dev/null @@ -1,46 +0,0 @@ -# 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), - } diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py new file mode 100644 index 000000000..46953c12e --- /dev/null +++ b/youtube_dl/extractor/comcarcoff.py @@ -0,0 +1,52 @@ +# encoding: utf-8 +import json + +from .common import InfoExtractor +from ..utils import parse_iso8601 + + +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', + 'ext': 'mp4', + 'upload_date': '20141127', + 'timestamp': 1417107600, + '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', + }, + 'params': { + 'skip_download': 'requires ffmpeg', + } + }] + + 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, 'full data json')) + + video_id = full_data['activeVideo']['video'] + video_data = full_data['videos'][video_id] + thumbnails = [{ + 'url': video_data['images']['thumb'], + }, { + 'url': video_data['images']['poster'], + }] + formats = self._extract_m3u8_formats( + video_data['mediaUrl'], video_id, ext='mp4') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': video_data['title'], + 'description': video_data.get('description'), + 'timestamp': parse_iso8601(video_data.get('pubDate')), + 'thumbnails': thumbnails, + 'formats': formats, + } |