Merge tag 'upstream/2014.07.11'

[youtubedl] / youtube_dl / extractor / zdf.py

diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py
index 35ece354a6ecdf7ba5705184d4ceff22d57eb3d4..3b1ac4e9f5246e268e0c0b49d64249196270e9d4 100644 (file)
--- a/youtube_dl/extractor/zdf.py
+++ b/youtube_dl/extractor/zdf.py
@@ -1,10 +1,11 @@
 # coding: utf-8
 # coding: utf-8

+from __future__ import unicode_literals

 
 

-import operator

 import re
 
 from .common import InfoExtractor
 from ..utils import (
 import re
 
 from .common import InfoExtractor
 from ..utils import (

+    int_or_none,

     unified_strdate,
 )
 
     unified_strdate,
 )
 


@@ -13,52 +14,42 @@ class ZDFIE(InfoExtractor):
     _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
 
     _TEST = {
     _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
 
     _TEST = {

-        u"url": u"http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt",
-        u"file": u"2037704.webm",
-        u"info_dict": {
-            u"upload_date": u"20131127",
-            u"description": u"Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial \"Ende des Machtpokers - Große Koalition für Deutschland\".",
-            u"uploader": u"spezial",
-            u"title": u"ZDFspezial - Ende des Machtpokers"
+        'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
+        'info_dict': {
+            'id': '2037704',
+            'ext': 'webm',
+            'title': 'ZDFspezial - Ende des Machtpokers',
+            'description': 'Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial "Ende des Machtpokers - Große Koalition für Deutschland".',
+            'duration': 1022,
+            'uploader': 'spezial',
+            'uploader_id': '225948',
+            'upload_date': '20131127',

         },
         },

-        u"skip": u"Videos on ZDF.de are depublicised in short order",
+        'skip': 'Videos on ZDF.de are depublicised in short order',

     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
 
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
 

-        xml_url = u'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
+        xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id

         doc = self._download_xml(
             xml_url, video_id,
         doc = self._download_xml(
             xml_url, video_id,

-            note=u'Downloading video info',
-            errnote=u'Failed to download video info')
+            note='Downloading video info',
+            errnote='Failed to download video info')

 
         title = doc.find('.//information/title').text
         description = doc.find('.//information/detail').text
 
         title = doc.find('.//information/title').text
         description = doc.find('.//information/detail').text

+        duration = int(doc.find('.//details/lengthSec').text)

         uploader_node = doc.find('.//details/originChannelTitle')
         uploader = None if uploader_node is None else uploader_node.text
         uploader_node = doc.find('.//details/originChannelTitle')
         uploader = None if uploader_node is None else uploader_node.text

-        duration_str = doc.find('.//details/length').text
-        duration_m = re.match(r'''(?x)^
-            (?P<hours>[0-9]{2})
-            :(?P<minutes>[0-9]{2})
-            :(?P<seconds>[0-9]{2})
-            (?:\.(?P<ms>[0-9]+)?)
-            ''', duration_str)
-        duration = (
-            (
-                (int(duration_m.group('hours')) * 60 * 60) +
-                (int(duration_m.group('minutes')) * 60) +
-                int(duration_m.group('seconds'))
-            )
-            if duration_m
-            else None
-        )
+        uploader_id_node = doc.find('.//details/originChannelId')
+        uploader_id = None if uploader_id_node is None else uploader_id_node.text

         upload_date = unified_strdate(doc.find('.//details/airtime').text)
 
         def xml_to_format(fnode):
             video_url = fnode.find('url').text
         upload_date = unified_strdate(doc.find('.//details/airtime').text)
 
         def xml_to_format(fnode):
             video_url = fnode.find('url').text

-            is_available = u'http://www.metafilegenerator' not in video_url
+            is_available = 'http://www.metafilegenerator' not in video_url

 
             format_id = fnode.attrib['basetype']
             format_m = re.match(r'''(?x)
 
             format_id = fnode.attrib['basetype']
             format_m = re.match(r'''(?x)


@@ -67,59 +58,52 @@ class ZDFIE(InfoExtractor):
             ''', format_id)
 
             ext = format_m.group('container')
             ''', format_id)
 
             ext = format_m.group('container')

-            is_supported = ext != 'f4f'
-
-            PROTO_ORDER = ['http', 'rtmp', 'rtsp']
-            try:
-                proto_pref = -PROTO_ORDER.index(format_m.group('proto'))
-            except ValueError:
-                proto_pref = -999
+            proto = format_m.group('proto').lower()

 
             quality = fnode.find('./quality').text
 
             quality = fnode.find('./quality').text

-            QUALITY_ORDER = ['veryhigh', '300', 'high', 'med', 'low']
-            try:
-                quality_pref = -QUALITY_ORDER.index(quality)
-            except ValueError:
-                quality_pref = -999
-

             abr = int(fnode.find('./audioBitrate').text) // 1000
             abr = int(fnode.find('./audioBitrate').text) // 1000

-            vbr = int(fnode.find('./videoBitrate').text) // 1000
-            pref = (is_available, is_supported,
-                    proto_pref, quality_pref, vbr, abr)
+            vbr_node = fnode.find('./videoBitrate')
+            vbr = None if vbr_node is None else int(vbr_node.text) // 1000

 
 

-            format_note = u''
-            if not is_supported:
-                format_note += u'(unsupported)'
+            width_node = fnode.find('./width')
+            width = None if width_node is None else int_or_none(width_node.text)
+            height_node = fnode.find('./height')
+            height = None if height_node is None else int_or_none(height_node.text)
+
+            format_note = ''

             if not format_note:
                 format_note = None
 
             return {
             if not format_note:
                 format_note = None
 
             return {

-                'format_id': format_id + u'-' + quality,
+                'format_id': format_id + '-' + quality,

                 'url': video_url,
                 'ext': ext,
                 'acodec': format_m.group('acodec'),
                 'vcodec': format_m.group('vcodec'),
                 'abr': abr,
                 'vbr': vbr,
                 'url': video_url,
                 'ext': ext,
                 'acodec': format_m.group('acodec'),
                 'vcodec': format_m.group('vcodec'),
                 'abr': abr,
                 'vbr': vbr,

-                'width': int(fnode.find('./width').text),
-                'height': int(fnode.find('./height').text),
-                'filesize': int(fnode.find('./filesize').text),
+                'width': width,
+                'height': height,
+                'filesize': int_or_none(fnode.find('./filesize').text),

                 'format_note': format_note,
                 'format_note': format_note,

-                '_pref': pref,
+                'protocol': proto,

                 '_available': is_available,
             }
 
         format_nodes = doc.findall('.//formitaeten/formitaet')
                 '_available': is_available,
             }
 
         format_nodes = doc.findall('.//formitaeten/formitaet')

-        formats = sorted(filter(lambda f: f['_available'],
-                                map(xml_to_format, format_nodes)),
-                         key=operator.itemgetter('_pref'))
+        formats = list(filter(
+            lambda f: f['_available'],
+            map(xml_to_format, format_nodes)))
+
+        self._sort_formats(formats)

 
         return {
             'id': video_id,
             'title': title,
 
         return {
             'id': video_id,
             'title': title,

-            'formats': formats,

             'description': description,
             'description': description,

-            'uploader': uploader,

             'duration': duration,
             'duration': duration,

+            'uploader': uploader,
+            'uploader_id': uploader_id,

             'upload_date': upload_date,
             'upload_date': upload_date,

-        }
+            'formats': formats,
+        }
\ No newline at end of file