aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/godtube.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2014-07-27 02:38:05 +0700
committerSergey M․ <dstftw@gmail.com>2014-07-27 02:38:05 +0700
commitcb3ff6fb01fd099ab4102d0f1212abb50e06e5ff (patch)
tree62c085df993832f782239ccaae5119f1d06895ff /youtube_dl/extractor/godtube.py
parent71aa656d134f728f7600a48f5015a8c84abe745d (diff)
[godtube] Add extractor (Closes #3367)
Diffstat (limited to 'youtube_dl/extractor/godtube.py')
-rw-r--r--youtube_dl/extractor/godtube.py58
1 files changed, 58 insertions, 0 deletions
diff --git a/youtube_dl/extractor/godtube.py b/youtube_dl/extractor/godtube.py
new file mode 100644
index 000000000..73bd6d890
--- /dev/null
+++ b/youtube_dl/extractor/godtube.py
@@ -0,0 +1,58 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ parse_duration,
+ parse_iso8601,
+)
+
+
+class GodTubeIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)'
+ _TESTS = [
+ {
+ 'url': 'https://www.godtube.com/watch/?v=0C0CNNNU',
+ 'md5': '77108c1e4ab58f48031101a1a2119789',
+ 'info_dict': {
+ 'id': '0C0CNNNU',
+ 'ext': 'mp4',
+ 'title': 'Woman at the well.',
+ 'duration': 159,
+ 'timestamp': 1205712000,
+ 'uploader': 'beverlybmusic',
+ 'upload_date': '20080317',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ },
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ config = self._download_xml(
+ 'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(),
+ video_id, 'Downloading player config XML')
+
+ video_url = config.find('.//file').text
+ uploader = config.find('.//author').text
+ timestamp = parse_iso8601(config.find('.//date').text)
+ duration = parse_duration(config.find('.//duration').text)
+ thumbnail = config.find('.//image').text
+
+ media = self._download_xml(
+ 'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML')
+
+ title = media.find('.//title').text
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'timestamp': timestamp,
+ 'uploader': uploader,
+ 'duration': duration,
+ }