Merge remote-tracking branch 'origin/master'

youtube_dl/__init__.py

@@ -65,6 +65,7 @@ __authors__  = (
     'Tobias Bell',
     'Naglis Jonaitis',
     'Charles Chen',
+    'Hassaan Ali',
 )
 
 __license__ = 'Public Domain'

youtube_dl/extractor/__init__.py

@@ -53,6 +53,7 @@ from .cnn import (
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
+from .cracked import CrackedIE
 from .criterion import CriterionIE
 from .crunchyroll import CrunchyrollIE
 from .cspan import CSpanIE
@@ -252,6 +253,7 @@ from .rutube import (
     RutubePersonIE,
 )
 from .rutv import RUTVIE
+from .sapo import SapoIE
 from .savefrom import SaveFromIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
@@ -399,6 +401,7 @@ from .youtube import (
     YoutubeUserIE,
     YoutubeWatchLaterIE,
 )
+
 from .zdf import ZDFIE
 
 

youtube_dl/extractor/cracked.py

@@ -0,0 +1,65 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    str_to_int,
+)
+
+
+class CrackedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
+    _TEST = {
+        'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
+        'md5': '4b29a5eeec292cd5eca6388c7558db9e',
+        'info_dict': {
+            'id': '19006',
+            'ext': 'mp4',
+            'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
+            'description': 'md5:3b909e752661db86007d10e5ec2df769',
+            'timestamp': 1405659600,
+            'upload_date': '20140718',
+        }
+    }
+
+    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'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL')
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+
+        timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False)
+        if timestamp:
+            timestamp = parse_iso8601(timestamp[:-6])
+
+        view_count = str_to_int(self._html_search_regex(
+            r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False))
+
+        m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
+        if m:
+            width = int(m.group('width'))
+            height = int(m.group('height'))
+        else:
+            width = height = None
+
+        return {
+            'id': video_id,
+            'url':video_url,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'height': height,
+            'width': width,
+        }

youtube_dl/extractor/francetv.py

@@ -48,7 +48,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetvinfo.fr'
-    _VALID_URL = r'https?://www\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
+    _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
@@ -211,7 +211,7 @@ class GenerationQuoiIE(InfoExtractor):
 
 class CultureboxIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'culturebox.francetvinfo.fr'
-    _VALID_URL = r'https?://culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
+    _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
 
     _TEST = {
         'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813',

youtube_dl/extractor/mlb.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class MLBIE(InfoExtractor):
-    _VALID_URL = r'http?://m\.mlb\.com/video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)'
+    _VALID_URL = r'https?://m\.mlb\.com/video/(?:topic/[\da-z_-]+/)?v(?P<id>n?\d+)'
     _TESTS = [
         {
             'url': 'http://m.mlb.com/video/topic/81536970/v34496663/mianym-stanton-practices-for-the-home-run-derby',

youtube_dl/extractor/sapo.py

@@ -0,0 +1,119 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+)
+
+
+class SapoIE(InfoExtractor):
+    IE_DESC = 'SAPO Vídeos'
+    _VALID_URL = r'https?://(?:(?:v2|www)\.)?videos\.sapo\.(?:pt|cv|ao|mz|tl)/(?P<id>[\da-zA-Z]{20})'
+
+    _TESTS = [
+        {
+            'url': 'http://videos.sapo.pt/UBz95kOtiWYUMTA5Ghfi',
+            'md5': '79ee523f6ecb9233ac25075dee0eda83',
+            'note': 'SD video',
+            'info_dict': {
+                'id': 'UBz95kOtiWYUMTA5Ghfi',
+                'ext': 'mp4',
+                'title': 'Benfica - Marcas na Hitória',
+                'description': 'md5:c9082000a128c3fd57bf0299e1367f22',
+                'duration': 264,
+                'uploader': 'tiago_1988',
+                'upload_date': '20080229',
+                'categories': ['benfica', 'cabral', 'desporto', 'futebol', 'geovanni', 'hooijdonk', 'joao', 'karel', 'lisboa', 'miccoli'],
+            },
+        },
+        {
+            'url': 'http://videos.sapo.pt/IyusNAZ791ZdoCY5H5IF',
+            'md5': '90a2f283cfb49193fe06e861613a72aa',
+            'note': 'HD video',
+            'info_dict': {
+                'id': 'IyusNAZ791ZdoCY5H5IF',
+                'ext': 'mp4',
+                'title': 'Codebits VII - Report',
+                'description': 'md5:6448d6fd81ce86feac05321f354dbdc8',
+                'duration': 144,
+                'uploader': 'codebits',
+                'upload_date': '20140427',
+                'categories': ['codebits', 'codebits2014'],
+            },
+        },
+        {
+            'url': 'http://v2.videos.sapo.pt/yLqjzPtbTimsn2wWBKHz',
+            'md5': 'e5aa7cc0bdc6db9b33df1a48e49a15ac',
+            'note': 'v2 video',
+            'info_dict': {
+                'id': 'yLqjzPtbTimsn2wWBKHz',
+                'ext': 'mp4',
+                'title': 'Hipnose Condicionativa 4',
+                'description': 'md5:ef0481abf8fb4ae6f525088a6dadbc40',
+                'duration': 692,
+                'uploader': 'sapozen',
+                'upload_date': '20090609',
+                'categories': ['condicionativa', 'heloisa', 'hipnose', 'miranda', 'sapo', 'zen'],
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        item = self._download_xml(
+            'http://rd3.videos.sapo.pt/%s/rss2' % video_id, video_id).find('./channel/item')
+
+        title = item.find('./title').text
+        description = item.find('./{http://videos.sapo.pt/mrss/}synopse').text
+        thumbnail = item.find('./{http://search.yahoo.com/mrss/}content').get('url')
+        duration = parse_duration(item.find('./{http://videos.sapo.pt/mrss/}time').text)
+        uploader = item.find('./{http://videos.sapo.pt/mrss/}author').text
+        upload_date = unified_strdate(item.find('./pubDate').text)
+        view_count = int(item.find('./{http://videos.sapo.pt/mrss/}views').text)
+        comment_count = int(item.find('./{http://videos.sapo.pt/mrss/}comment_count').text)
+        tags = item.find('./{http://videos.sapo.pt/mrss/}tags').text
+        categories = tags.split() if tags else []
+        age_limit = 18 if item.find('./{http://videos.sapo.pt/mrss/}m18').text == 'true' else 0
+
+        video_url = item.find('./{http://videos.sapo.pt/mrss/}videoFile').text
+        video_size = item.find('./{http://videos.sapo.pt/mrss/}videoSize').text.split('x')
+
+        formats = [{
+            'url': video_url,
+            'ext': 'mp4',
+            'format_id': 'sd',
+            'width': int(video_size[0]),
+            'height': int(video_size[1]),
+        }]
+
+        if item.find('./{http://videos.sapo.pt/mrss/}HD').text == 'true':
+            formats.append({
+                'url': re.sub(r'/mov/1$', '/mov/39', video_url),
+                'ext': 'mp4',
+                'format_id': 'hd',
+                'width': 1280,
+                'height': 720,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/utils.py

@@ -1194,6 +1194,8 @@ def format_bytes(bytes):
 
 
 def str_to_int(int_str):
+    if int_str is None:
+        return None
     int_str = re.sub(r'[,\.]', u'', int_str)
     return int(int_str)