summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <[email protected]>2014-03-29 14:20:53 +0100
committerJaime Marquínez Ferrándiz <[email protected]>2014-03-29 14:22:28 +0100
commit79bfd01001ece4629d5370ec9dbff77b0c187eb5 (patch)
tree50dbc49e95fc5f033e7e083ed7b383fb9cf668d6
parentf2bcdd8e02c43b04c1df7346fdfddb18dbf6070f (diff)
downloadyoutube-dl-79bfd01001ece4629d5370ec9dbff77b0c187eb5.tar.gz
youtube-dl-79bfd01001ece4629d5370ec9dbff77b0c187eb5.zip
[kickstarter] Fix extraction, extract more info and modernize
-rw-r--r--youtube_dl/extractor/kickstarter.py46
1 files changed, 24 insertions, 22 deletions
diff --git a/youtube_dl/extractor/kickstarter.py b/youtube_dl/extractor/kickstarter.py
index 50bc883ef..961dd1aa6 100644
--- a/youtube_dl/extractor/kickstarter.py
+++ b/youtube_dl/extractor/kickstarter.py
@@ -1,37 +1,39 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
class KickStarterIE(InfoExtractor):
- _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>\d*)/.*'
+ _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*'
_TEST = {
- u"url": u"https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location",
- u"file": u"1404461844.mp4",
- u"md5": u"c81addca81327ffa66c642b5d8b08cab",
- u"info_dict": {
- u"title": u"Intersection: The Story of Josh Grant by Kyle Cowling",
+ 'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location',
+ 'md5': 'c81addca81327ffa66c642b5d8b08cab',
+ 'info_dict': {
+ 'id': '1404461844',
+ 'ext': 'mp4',
+ 'title': 'Intersection: The Story of Josh Grant by Kyle Cowling',
+ 'description': 'A unique motocross documentary that examines the '
+ 'life and mind of one of sports most elite athletes: Josh Grant.',
},
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
- webpage_src = self._download_webpage(url, video_id)
+ webpage = self._download_webpage(url, video_id)
- video_url = self._search_regex(r'data-video="(.*?)">',
- webpage_src, u'video URL')
- if 'mp4' in video_url:
- ext = 'mp4'
- else:
- ext = 'flv'
- video_title = self._html_search_regex(r"<title>(.*?)</title>",
- webpage_src, u'title').rpartition(u'\u2014 Kickstarter')[0].strip()
+ video_url = self._search_regex(r'data-video-url="(.*?)"',
+ webpage, 'video URL')
+ video_title = self._html_search_regex(r'<title>(.*?)</title>',
+ webpage, 'title').rpartition('— Kickstarter')[0].strip()
- results = [{
- 'id': video_id,
- 'url': video_url,
- 'title': video_title,
- 'ext': ext,
- }]
- return results
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': video_title,
+ 'description': self._og_search_description(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ }