aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/dailymotion.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2013-06-23 20:09:47 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2013-06-23 20:12:03 +0200
commit219b8130dfe564701a0ebd27bedfba7785b24b52 (patch)
treef985566587a0e0d6f10919cf84ded0f9ed829f59 /youtube_dl/extractor/dailymotion.py
parent38cbc40a64513718228ad14cdb616cf955246224 (diff)
Move DailyMotion into its own file
Diffstat (limited to 'youtube_dl/extractor/dailymotion.py')
-rw-r--r--youtube_dl/extractor/dailymotion.py77
1 files changed, 77 insertions, 0 deletions
diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
new file mode 100644
index 000000000..34306b073
--- /dev/null
+++ b/youtube_dl/extractor/dailymotion.py
@@ -0,0 +1,77 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_request,
+ compat_urllib_parse,
+
+ ExtractorError,
+ unescapeHTML,
+)
+
+class DailymotionIE(InfoExtractor):
+ """Information Extractor for Dailymotion"""
+
+ _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
+ IE_NAME = u'dailymotion'
+
+ def _real_extract(self, url):
+ # Extract id and simplified title from URL
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group(1).split('_')[0].split('?')[0]
+
+ video_extension = 'mp4'
+
+ # Retrieve video webpage to extract further information
+ request = compat_urllib_request.Request(url)
+ request.add_header('Cookie', 'family_filter=off')
+ webpage = self._download_webpage(request, video_id)
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'\s*var flashvars = (.*)', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract media URL')
+ flashvars = compat_urllib_parse.unquote(mobj.group(1))
+
+ for key in ['hd1080URL', 'hd720URL', 'hqURL', 'sdURL', 'ldURL', 'video_url']:
+ if key in flashvars:
+ max_quality = key
+ self.to_screen(u'Using %s' % key)
+ break
+ else:
+ raise ExtractorError(u'Unable to extract video URL')
+
+ mobj = re.search(r'"' + max_quality + r'":"(.+?)"', flashvars)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract video URL')
+
+ video_url = compat_urllib_parse.unquote(mobj.group(1)).replace('\\/', '/')
+
+ # TODO: support choosing qualities
+
+ mobj = re.search(r'<meta property="og:title" content="(?P<title>[^"]*)" />', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract title')
+ video_title = unescapeHTML(mobj.group('title'))
+
+ video_uploader = None
+ video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
+ # Looking for official user
+ r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
+ webpage, 'video uploader')
+
+ video_upload_date = None
+ mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
+ if mobj is not None:
+ video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'uploader': video_uploader,
+ 'upload_date': video_upload_date,
+ 'title': video_title,
+ 'ext': video_extension,
+ }]