release 2014.08.02

youtube_dl/extractor/__init__.py

@@ -143,6 +143,7 @@ from .ivi import (
     IviIE,
     IviCompilationIE
 )
+from .izlesene import IzleseneIE
 from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
@@ -347,6 +348,7 @@ from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
+from .vidme import VidmeIE
 from .vimeo import (
     VimeoIE,
     VimeoChannelIE,

youtube_dl/extractor/ard.py

@@ -8,6 +8,8 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     qualities,
+    compat_urllib_parse_urlparse,
+    compat_urllib_parse,
 )
 
 
@@ -44,6 +46,9 @@ class ARDIE(InfoExtractor):
         else:
             video_id = m.group('video_id')
 
+        urlp = compat_urllib_parse_urlparse(url)
+        url = urlp._replace(path=compat_urllib_parse.quote(urlp.path.encode('utf-8'))).geturl()
+
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(

youtube_dl/extractor/izlesene.py

@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    get_element_by_id,
+    parse_iso8601,
+    determine_ext,
+    int_or_none,
+    str_to_int,
+)
+
+
+class IzleseneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
+    _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
+    _TEST = {
+        'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
+        'md5': '4384f9f0ea65086734b881085ee05ac2',
+        'info_dict': {
+            'id': '7599694',
+            'ext': 'mp4',
+            'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
+            'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
+            'thumbnail': 're:^http://.*\.jpg',
+            'uploader_id': 'pelikzzle',
+            'timestamp': 1404298698,
+            'upload_date': '20140702',
+            'duration': 95.395,
+            'age_limit': 0,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        url = 'http://www.izlesene.com/video/%s' % video_id
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        uploader = self._html_search_regex(
+            r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage, 'upload date', fatal=False))
+
+        duration = int_or_none(self._html_search_regex(
+            r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False))
+        if duration:
+            duration /= 1000.0
+
+        view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
+        comment_count = self._html_search_regex(
+            r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False)
+
+        family_friendly = self._html_search_meta(
+            'isFamilyFriendly', webpage, 'age limit', fatal=False)
+
+        content_url = self._html_search_meta(
+            'contentURL', webpage, 'content URL', fatal=False)
+        ext = determine_ext(content_url, 'mp4')
+
+        # Might be empty for some videos.
+        qualities = self._html_search_regex(
+            r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='')
+
+        formats = []
+        for quality in qualities.split('|'):
+            json = self._download_json(
+                self._STREAM_URL.format(id=video_id, format=quality), video_id,
+                note='Getting video URL for "%s" quality' % quality,
+                errnote='Failed to get video URL for "%s" quality' % quality
+            )
+            formats.append({
+                'url': json.get('streamurl'),
+                'ext': ext,
+                'format_id': '%sp' % quality if quality else 'sd',
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader_id': uploader,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+            'age_limit': 18 if family_friendly == 'False' else 0,
+            'formats': formats,
+        }

youtube_dl/extractor/vidme.py

@@ -0,0 +1,68 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    str_to_int,
+)
+
+
+class VidmeIE(InfoExtractor):
+    _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
+    _TEST = {
+        'url': 'https://vid.me/QNB',
+        'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
+        'info_dict': {
+            'id': 'QNB',
+            'ext': 'mp4',
+            'title': 'Fishing for piranha - the easy way',
+            'description': 'source: https://www.facebook.com/photo.php?v=312276045600871',
+            'duration': 119.92,
+            'timestamp': 1406313244,
+            'upload_date': '20140725',
+            'thumbnail': 're:^https?://.*\.jpg',
+        },
+    }
+
+    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'<source src="([^"]+)"', webpage, 'video URL')
+
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage, default='')
+        thumbnail = self._og_search_thumbnail(webpage)
+        timestamp = int_or_none(self._og_search_property('updated_time', webpage, fatal=False))
+        width = int_or_none(self._og_search_property('video:width', webpage, fatal=False))
+        height = int_or_none(self._og_search_property('video:height', webpage, fatal=False))
+        duration = float_or_none(self._html_search_regex(
+            r'data-duration="([^"]+)"', webpage, 'duration', fatal=False))
+        view_count = str_to_int(self._html_search_regex(
+            r'<span class="video_views">\s*([\d,\.]+)\s*plays?', webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._html_search_regex(
+            r'class="score js-video-vote-score"[^>]+data-score="([\d,\.\s]+)">',
+            webpage, 'like count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'class="js-comment-count"[^>]+data-count="([\d,\.\s]+)">',
+            webpage, 'comment count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'width': width,
+            'height': height,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': like_count,
+            'comment_count': comment_count,
+        }

youtube_dl/extractor/youtube.py

@@ -344,7 +344,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         """Indicate the download will use the RTMP protocol."""
         self.to_screen(u'RTMP download detected')
 
-    def _extract_signature_function(self, video_id, player_url, slen):
+    def _signature_cache_id(self, example_sig):
+        """ Return a string representation of a signature """
+        return u'.'.join(compat_str(len(part)) for part in example_sig.split('.'))
+
+    def _extract_signature_function(self, video_id, player_url, example_sig):
         id_m = re.match(
             r'.*-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$',
             player_url)
@@ -354,7 +358,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         player_id = id_m.group('id')
 
         # Read from filesystem cache
-        func_id = '%s_%s_%d' % (player_type, player_id, slen)
+        func_id = '%s_%s_%s' % (
+            player_type, player_id, self._signature_cache_id(example_sig))
         assert os.path.basename(func_id) == func_id
         cache_dir = get_cachedir(self._downloader.params)
 
@@ -388,7 +393,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
         if cache_enabled:
             try:
-                test_string = u''.join(map(compat_chr, range(slen)))
+                test_string = u''.join(map(compat_chr, range(len(example_sig))))
                 cache_res = res(test_string)
                 cache_spec = [ord(c) for c in cache_res]
                 try:
@@ -404,7 +409,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
         return res
 
-    def _print_sig_code(self, func, slen):
+    def _print_sig_code(self, func, example_sig):
         def gen_sig_code(idxs):
             def _genslice(start, end, step):
                 starts = u'' if start == 0 else str(start)
@@ -433,11 +438,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             else:
                 yield _genslice(start, i, step)
 
-        test_string = u''.join(map(compat_chr, range(slen)))
+        test_string = u''.join(map(compat_chr, range(len(example_sig))))
         cache_res = func(test_string)
         cache_spec = [ord(c) for c in cache_res]
         expr_code = u' + '.join(gen_sig_code(cache_spec))
-        code = u'if len(s) == %d:\n    return %s\n' % (slen, expr_code)
+        signature_id_tuple = '(%s)' % (
+            ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
+        code = (u'if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
+                u'    return %s\n') % (signature_id_tuple, expr_code)
         self.to_screen(u'Extracted signature function:\n' + code)
 
     def _parse_sig_js(self, jscode):
@@ -465,20 +473,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         if player_url.startswith(u'//'):
             player_url = u'https:' + player_url
         try:
-            player_id = (player_url, len(s))
+            player_id = (player_url, self._signature_cache_id(s))
             if player_id not in self._player_cache:
                 func = self._extract_signature_function(
-                    video_id, player_url, len(s)
+                    video_id, player_url, s
                 )
                 self._player_cache[player_id] = func
             func = self._player_cache[player_id]
             if self._downloader.params.get('youtube_print_sig_code'):
-                self._print_sig_code(func, len(s))
+                self._print_sig_code(func, s)
             return func(s)
         except Exception as e:
             tb = traceback.format_exc()
             raise ExtractorError(
-                u'Automatic signature extraction failed: ' + tb, cause=e)
+                u'Signature extraction failed: ' + tb, cause=e)
 
     def _get_available_subtitles(self, video_id, webpage):
         try:
@@ -806,51 +814,54 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             url_map = {}
             for url_data_str in encoded_url_map.split(','):
                 url_data = compat_parse_qs(url_data_str)
-                if 'itag' in url_data and 'url' in url_data:
-                    url = url_data['url'][0]
-                    if 'sig' in url_data:
-                        url += '&signature=' + url_data['sig'][0]
-                    elif 's' in url_data:
-                        encrypted_sig = url_data['s'][0]
+                if 'itag' not in url_data or 'url' not in url_data:
+                    continue
+                format_id = url_data['itag'][0]
+                url = url_data['url'][0]
 
-                        if not age_gate:
-                            jsplayer_url_json = self._search_regex(
-                                r'"assets":.+?"js":\s*("[^"]+")',
-                                video_webpage, u'JS player URL')
-                            player_url = json.loads(jsplayer_url_json)
+                if 'sig' in url_data:
+                    url += '&signature=' + url_data['sig'][0]
+                elif 's' in url_data:
+                    encrypted_sig = url_data['s'][0]
+
+                    if not age_gate:
+                        jsplayer_url_json = self._search_regex(
+                            r'"assets":.+?"js":\s*("[^"]+")',
+                            video_webpage, u'JS player URL')
+                        player_url = json.loads(jsplayer_url_json)
+                    if player_url is None:
+                        player_url_json = self._search_regex(
+                            r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
+                            video_webpage, u'age gate player URL')
+                        player_url = json.loads(player_url_json)
+
+                    if self._downloader.params.get('verbose'):
                         if player_url is None:
-                            player_url_json = self._search_regex(
-                                r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
-                                video_webpage, u'age gate player URL')
-                            player_url = json.loads(player_url_json)
-
-                        if self._downloader.params.get('verbose'):
-                            if player_url is None:
-                                player_version = 'unknown'
-                                player_desc = 'unknown'
+                            player_version = 'unknown'
+                            player_desc = 'unknown'
+                        else:
+                            if player_url.endswith('swf'):
+                                player_version = self._search_regex(
+                                    r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
+                                    u'flash player', fatal=False)
+                                player_desc = 'flash player %s' % player_version
                             else:
-                                if player_url.endswith('swf'):
-                                    player_version = self._search_regex(
-                                        r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
-                                        u'flash player', fatal=False)
-                                    player_desc = 'flash player %s' % player_version
-                                else:
-                                    player_version = self._search_regex(
-                                        r'html5player-([^/]+?)(?:/html5player)?\.js',
-                                        player_url,
-                                        'html5 player', fatal=False)
-                                    player_desc = u'html5 player %s' % player_version
+                                player_version = self._search_regex(
+                                    r'html5player-([^/]+?)(?:/html5player)?\.js',
+                                    player_url,
+                                    'html5 player', fatal=False)
+                                player_desc = u'html5 player %s' % player_version
 
-                            parts_sizes = u'.'.join(compat_str(len(part)) for part in encrypted_sig.split('.'))
-                            self.to_screen(u'encrypted signature length %d (%s), itag %s, %s' %
-                                (len(encrypted_sig), parts_sizes, url_data['itag'][0], player_desc))
+                        parts_sizes = self._signature_cache_id(encrypted_sig)
+                        self.to_screen(u'{%s} signature length %s, %s' %
+                            (format_id, parts_sizes, player_desc))
 
-                        signature = self._decrypt_signature(
-                            encrypted_sig, video_id, player_url, age_gate)
-                        url += '&signature=' + signature
-                    if 'ratebypass' not in url:
-                        url += '&ratebypass=yes'
-                    url_map[url_data['itag'][0]] = url
+                    signature = self._decrypt_signature(
+                        encrypted_sig, video_id, player_url, age_gate)
+                    url += '&signature=' + signature
+                if 'ratebypass' not in url:
+                    url += '&ratebypass=yes'
+                url_map[format_id] = url
             formats = _map_to_format_list(url_map)
         elif video_info.get('hlsvp'):
             manifest_url = video_info['hlsvp'][0]

youtube_dl/utils.py

@@ -852,6 +852,8 @@ def unified_strdate(date_str):
     return upload_date
 
 def determine_ext(url, default_ext=u'unknown_video'):
+    if url is None:
+        return default_ext
     guess = url.partition(u'?')[0].rpartition(u'.')[2]
     if re.match(r'^[A-Za-z0-9]+$', guess):
         return guess

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.07.30'
+__version__ = '2014.08.02'