aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-04-11 19:34:06 +0600
committerSergey M․ <dstftw@gmail.com>2015-04-11 19:34:06 +0600
commitaf14ded75e10653b4713c23f8c428c6cd88610ad (patch)
treeefdf03d17ec71a4c5930af9be3cbd45f2ef38dd3 /youtube_dl/extractor
parent65939effb55087f584ecd5d4b304eadbdef875d1 (diff)
parent6e53c91608d1c43a9fe1614f13a15db74e877a91 (diff)
Merge branch 'crooksandliars' of https://github.com/fstirlitz/youtube-dl into fstirlitz-crooksandliars
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/crooksandliars.py71
2 files changed, 72 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 8df1db83e..894aa5b43 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -90,6 +90,7 @@ from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE
+from .crooksandliars import CrooksAndLiarsIE, CrooksAndLiarsArticleIE
from .crunchyroll import (
CrunchyrollIE,
CrunchyrollShowPlaylistIE
diff --git a/youtube_dl/extractor/crooksandliars.py b/youtube_dl/extractor/crooksandliars.py
new file mode 100644
index 000000000..cee0603f4
--- /dev/null
+++ b/youtube_dl/extractor/crooksandliars.py
@@ -0,0 +1,71 @@
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ mimetype2ext,
+)
+
+
+class CrooksAndLiarsIE(InfoExtractor):
+ _VALID_URL = r'(?:https?:)?//embed.crooksandliars.com/embed/(?P<id>[A-Za-z0-9]+)(?:$|[?#])'
+
+ _TESTS = [{
+ 'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
+ 'info_dict': {
+ 'id': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
+ 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
+ 'description': "Fox News, Fox & Friends Weekend, April 4, 2015. Read more... http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists",
+ 'timestamp': 1428207000,
+ 'thumbnail': 'https://crooksandliars.com/files/mediaposters/2015/04/31235.jpg?ts=1428207050',
+ 'uploader': "Heather",
+ }
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ manifest = json.loads(self._html_search_regex(r'var manifest = ({.*?})\n', webpage, 'manifest JSON'))
+
+ formats = []
+ for item in manifest['flavors']:
+ if not item['mime'].startswith('video/'): # XXX: or item['exclude']?
+ continue
+ formats.append({
+ 'format_id': item['type'],
+ 'ext': mimetype2ext(item['mime']),
+ 'url': item['url'],
+ })
+
+ # XXX: manifest['url']?
+ return {
+ 'url': url,
+ 'id': video_id,
+ 'uploader': manifest['author'],
+ 'title': manifest['title'],
+ 'description': manifest['description'],
+ 'thumbnail': self._proto_relative_url(manifest['poster']),
+ 'duration': manifest['duration'],
+ 'timestamp': int(manifest['created']),
+ 'formats': formats,
+ }
+
+class CrooksAndLiarsArticleIE(InfoExtractor):
+ _VALID_URL = r'(?:https?:)?//crooksandliars.com/\d+/\d+/(?P<id>[a-z\-]+)(?:/|$)'
+
+ _TESTS = [{
+ 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ player_url = self._proto_relative_url(self._html_search_regex(r'<iframe src="(//embed.crooksandliars.com/.*)"', webpage, 'embedded player'))
+
+ return {
+ '_type': 'url',
+ 'url': player_url
+ }