aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-08-31 23:57:51 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2014-08-31 23:57:51 +0200
commit2d7af094879401db25330cfddcdb81bbc1dadb2b (patch)
treea88ec8fff316276e092ff69334db3a3a14bf4e5e /youtube_dl
parent48d4681efcb02455722e15b0183bd42ab50dc748 (diff)
parent2aebbccefceec3eb2cad147204123cb28b9d81d1 (diff)
Merge remote-tracking branch 'peugeot/beeg'
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/beeg.py48
2 files changed, 49 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 1c305fcc4..9f43bb8f4 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -24,6 +24,7 @@ from .auengine import AUEngineIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbccouk import BBCCoUkIE
+from .beeg import BeegIE
from .bilibili import BiliBiliIE
from .blinkx import BlinkxIE
from .bliptv import BlipTVIE, BlipTVUserIE
diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
new file mode 100644
index 000000000..775f6be6b
--- /dev/null
+++ b/youtube_dl/extractor/beeg.py
@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class BeegIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://beeg.com/5416503',
+ 'md5': '634526ae978711f6b748fe0dd6c11f57',
+ 'info_dict': {
+ 'id': '5416503',
+ 'ext': 'mp4',
+ 'title': 'Sultry Striptease',
+ 'description': 'md5:6db3c6177972822aaba18652ff59c773',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, video_id)
+
+ video_url = self._html_search_regex(r"'480p'\s*:\s*'([^']+)'", webpage, 'video URL')
+
+ title = self._html_search_regex(r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
+
+ description = self._html_search_regex(
+ r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False)
+
+ thumbnail = self._html_search_regex(
+ r'\'previewer.url\'\s*:\s*"([^"]*)"', webpage, 'thumbnail', fatal=False)
+
+ categories_str = self._html_search_regex(
+ r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
+ categories = categories_str.split(',')
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'categories': categories,
+ }