aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/comcarcoff.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-12-12 20:32:02 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2014-12-12 20:32:02 +0100
commitdc5596ff54860dc470579c17f4b072266f44cf5c (patch)
treee24d228402d7b2e2548a301b6789e1a21d18ce0b /youtube_dl/extractor/comcarcoff.py
parent46d9760f5ebd86ee5b34fd669f44b124f34fffc1 (diff)
[comcarcoff] (#4454)
Diffstat (limited to 'youtube_dl/extractor/comcarcoff.py')
-rw-r--r--youtube_dl/extractor/comcarcoff.py52
1 files changed, 52 insertions, 0 deletions
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,
+ }