universcience 2

youtube_dl/extractor/canalu.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class CanalUIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://yourextractor.com/watch/42',
+        'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
+        'info_dict': {
+            'id': '42',
+            'ext': 'mp4',
+            'title': 'Video title goes here',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            # TODO more properties, either as:
+            # * A value
+            # * MD5 checksum; start the string with md5:
+            # * A regular expression; start the string with re:
+            # * Any Python type (for example int or float)
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # TODO more code goes here, for example ...
+        title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._og_search_description(webpage),
+            'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
+            # TODO more properties (see youtube_dl/extractor/common.py)
+        }

youtube_dl/extractor/extractors.py

@@ -116,6 +116,7 @@ from .camdemy import (
 from .camwithher import CamWithHerIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
+from .canalu import CanalUIE
 from .canvas import CanvasIE
 from .carambatv import (
     CarambaTVIE,

youtube_dl/extractor/universcience.py

@@ -8,11 +8,12 @@ from ..utils import (
     xpath_element,
     xpath_attr,
     clean_html,
+    update_url_query,
 )
 
 
 class UniverscienceIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?universcience\.tv/video-(.*)-(?P<id>[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?universcience\.tv/video-.*-(?P<id>[0-9]+)\.html'
     _TEST = {
         'url': 'http://www.universcience.tv/video-haro-sur-les-loups-o-5466.html',
         'info_dict': {
@@ -34,8 +35,10 @@ class UniverscienceIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        APIKey = self._html_search_regex(r'["\']APIKey["\'](.*)["\'](?P<APIKey>.*)["\']', webpage, 'APIKey', group='APIKey')
+        APIKey = self._html_search_regex(r'["\']APIKey["\'].*["\'](?P<APIKey>.*)["\']', webpage, 'APIKey', group='APIKey')
-        url_get_media = 'http://universcience-webtv2-services-pad.brainsonic.com/rest/getMedia?APIKey=' + APIKey + '&byMediaId=' + video_id
+        url_get_media = update_url_query(
+            'http://universcience-webtv2-services-pad.brainsonic.com/rest/getMedia',
+            {'APIKey': APIKey, 'byMediaId': video_id})
         xml = self._download_xml(url_get_media, video_id)
         path_media = xpath_element(xml, './medias/media', fatal=True)
 
@@ -58,20 +61,18 @@ class UniverscienceIE(InfoExtractor):
         for media_source in xml.findall(path_media_source):
             format_url = xpath_text(media_source, 'source', fatal=True)
             media_label = xpath_attr(media_source, './streaming_type', 'label')
-            media_width = self._search_regex(
+            media_width = int_or_none(self._search_regex(r'(\d*) x \d*', media_label, 'width', default=None))
-                r'.* (\d*) x \d*', media_label, 'width', default='None', fatal=False)
+            media_height = int_or_none(self._search_regex(r'\d* x (\d*)', media_label, 'height', default=None))
-            media_height = self._search_regex(
-                r'.* \d* x (\d*)', media_label, 'height', default='None', fatal=False)
             media_label = self._search_regex(
                 r'(.*) (\d* x \d*)', media_label, 'media_label', default=media_label, fatal=False)
 
-            if (media_label == 'HLS') or (media_label == 'm3u8'):
+            if media_label in ('HLS', 'm3u8'):
                 formats.extend(self._extract_m3u8_formats(
                     format_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False))
             else:
                 format_info = {
-                    'width': int_or_none(media_width),
+                    'width': media_width,
-                    'height': int_or_none(media_height),
+                    'height': media_height,
                     'tbr': int_or_none(xpath_attr(media_source, './streaming_type', 'bitrate')),
                     # 'vcodec': xpath_attr -> bug sur regexp?
                     'vcodec': media_source.find('streaming_type').get('html5_codec'),
@@ -81,6 +82,7 @@ class UniverscienceIE(InfoExtractor):
                 formats.append(format_info)
 
         podcast_url = xpath_text(path_media, './podcast_url')
+        if podcast_url is not None:
             formats.append({'format_id': 'podcast', 'vcodec': 'none', 'url': podcast_url})
 
         self._sort_formats(formats)