aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nosvideo.py
diff options
context:
space:
mode:
authorNaglis Jonaitis <njonaitis@gmail.com>2014-09-01 23:47:14 +0300
committerNaglis Jonaitis <njonaitis@gmail.com>2014-09-01 23:47:14 +0300
commit49fa38adf2ff1114fc51e89d796a9cbf91622068 (patch)
treeebcdc3dd9cfa5e8774b9ca455e807c728c8a7382 /youtube_dl/extractor/nosvideo.py
parent61edcfb0a2dd9a870657ae71fe5856da3bab2ac4 (diff)
[nosvideo] Add new extractor
Diffstat (limited to 'youtube_dl/extractor/nosvideo.py')
-rw-r--r--youtube_dl/extractor/nosvideo.py68
1 files changed, 68 insertions, 0 deletions
diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py
new file mode 100644
index 000000000..dbb03613b
--- /dev/null
+++ b/youtube_dl/extractor/nosvideo.py
@@ -0,0 +1,68 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse,
+ compat_urllib_request,
+ determine_ext,
+ xpath_with_ns,
+)
+
+_x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
+_find = lambda el, p: el.find(_x(p)).text.strip()
+
+
+class NosVideoIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
+ '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
+ _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
+ _TEST = {
+ 'url': 'http://nosvideo.com/?v=drlp6s40kg54',
+ 'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c',
+ 'info_dict': {
+ 'id': 'drlp6s40kg54',
+ 'ext': 'mp4',
+ 'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ fields = {
+ 'id': video_id,
+ 'op': 'download1',
+ 'method_free': 'Continue to Video',
+ }
+ post = compat_urllib_parse.urlencode(fields)
+ req = compat_urllib_request.Request(url, post)
+ req.add_header('Content-type', 'application/x-www-form-urlencoded')
+ webpage = self._download_webpage(req, video_id,
+ 'Downloading download page')
+ xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
+ playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
+ playlist = self._download_xml(playlist_url, video_id)
+
+ track = playlist.find(_x('.//xspf:track'))
+ title = _find(track, './xspf:title')
+ url = _find(track, './xspf:file')
+ thumbnail = _find(track, './xspf:image')
+ ext = determine_ext(title)
+
+ formats = [{
+ 'format_id': 'sd',
+ 'url': url,
+ 'ext': ext,
+ }]
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'formats': formats,
+ }