Imported Upstream version 2015.11.10

[youtubedl] / youtube_dl / extractor / iprima.py

diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py
index dde4829981a7adab396a040ccc1566277c39194b..821c8ec109236b787b9afa2985e450ff8a647595 100644 (file)
--- a/youtube_dl/extractor/iprima.py
+++ b/youtube_dl/extractor/iprima.py
@@ -6,11 +6,17 @@ from random import random
 from math import floor
 
 from .common import InfoExtractor
 from math import floor
 
 from .common import InfoExtractor

-from ..utils import compat_urllib_request
+from ..compat import (
+    compat_urllib_request,
+)
+from ..utils import (
+    ExtractorError,
+    remove_end,
+)

 
 
 class IPrimaIE(InfoExtractor):
 
 
 class IPrimaIE(InfoExtractor):

-    _VALID_URL = r'https?://play\.iprima\.cz/(?P<videogroup>.+)/(?P<videoid>.+)'
+    _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'

 
     _TESTS = [{
         'url': 'http://play.iprima.cz/particka/particka-92',
 
     _TESTS = [{
         'url': 'http://play.iprima.cz/particka/particka-92',


@@ -18,24 +24,42 @@ class IPrimaIE(InfoExtractor):
             'id': '39152',
             'ext': 'flv',
             'title': 'Partička (92)',
             'id': '39152',
             'ext': 'flv',
             'title': 'Partička (92)',

-            'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
+            'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',

             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
         },
         'params': {
             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
         },
         'params': {

-            'skip_download': True,
+            'skip_download': True,  # requires rtmpdump

         },
         },

-    },
-    ]
+    }, {
+        'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
+        'info_dict': {
+            'id': '9718337',
+            'ext': 'flv',
+            'title': 'Tchibo Partička - Jarní móda',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }, {
+        'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')

 
         webpage = self._download_webpage(url, video_id)
 
 
         webpage = self._download_webpage(url, video_id)
 

-        player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % (
-                         floor(random()*1073741824),
-                         floor(random()*1073741824))
+        if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*</div>', webpage):
+            raise ExtractorError(
+                '%s said: You do not have permission to access this page' % self.IE_NAME, expected=True)
+
+        player_url = (
+            'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
+            (floor(random() * 1073741824), floor(random() * 1073741824))
+        )

 
         req = compat_urllib_request.Request(player_url)
         req.add_header('Referer', url)
 
         req = compat_urllib_request.Request(player_url)
         req.add_header('Referer', url)


@@ -44,18 +68,20 @@ class IPrimaIE(InfoExtractor):
         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
 
         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
 
         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')

-

         if zoneGEO != '0':
         if zoneGEO != '0':

-            base_url = base_url.replace('token', 'token_'+zoneGEO)
+            base_url = base_url.replace('token', 'token_' + zoneGEO)

 
         formats = []
         for format_id in ['lq', 'hq', 'hd']:
 
         formats = []
         for format_id in ['lq', 'hq', 'hd']:

-            filename = self._html_search_regex(r'"%s_id":(.+?),' % format_id, webpage, 'filename')
+            filename = self._html_search_regex(
+                r'"%s_id":(.+?),' % format_id, webpage, 'filename')

 
             if filename == 'null':
                 continue
 
 
             if filename == 'null':
                 continue
 

-            real_id = self._search_regex(r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id')
+            real_id = self._search_regex(
+                r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
+                filename, 'real video id')

 
             if format_id == 'lq':
                 quality = 0
 
             if format_id == 'lq':
                 quality = 0


@@ -63,13 +89,13 @@ class IPrimaIE(InfoExtractor):
                 quality = 1
             elif format_id == 'hd':
                 quality = 2
                 quality = 1
             elif format_id == 'hd':
                 quality = 2

-                filename = 'hq/'+filename
+                filename = 'hq/' + filename

 
             formats.append({
                 'format_id': format_id,
                 'url': base_url,
                 'quality': quality,
 
             formats.append({
                 'format_id': format_id,
                 'url': base_url,
                 'quality': quality,

-                'play_path': 'mp4:'+filename.replace('"', '')[:-4],
+                'play_path': 'mp4:' + filename.replace('"', '')[:-4],

                 'rtmp_live': True,
                 'ext': 'flv',
             })
                 'rtmp_live': True,
                 'ext': 'flv',
             })


@@ -78,8 +104,10 @@ class IPrimaIE(InfoExtractor):
 
         return {
             'id': real_id,
 
         return {
             'id': real_id,

-            'title': self._og_search_title(webpage),
+            'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'),

             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,
             'thumbnail': self._og_search_thumbnail(webpage),
             'formats': formats,

-            'description': self._og_search_description(webpage),
+            'description': self._search_regex(
+                r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
+                webpage, 'description', default=None),

         }
         }