Prepare for release.

[youtubedl] / youtube_dl / extractor / orf.py

diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py
index 958eb398b992e4d3b4278ebe362f71074e87c19b..b4cce7ea9334c7bbaf9e617932189504dcd25121 100644 (file)
--- a/youtube_dl/extractor/orf.py
+++ b/youtube_dl/extractor/orf.py
@@ -1,28 +1,28 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

-import json

 import re
 import calendar
 import datetime
 
 from .common import InfoExtractor
 import re
 import calendar
 import datetime
 
 from .common import InfoExtractor

+from ..compat import compat_str

 from ..utils import (
     HEADRequest,
     unified_strdate,
 from ..utils import (
     HEADRequest,
     unified_strdate,

-    ExtractorError,

     strip_jsonp,
     int_or_none,
     float_or_none,
     determine_ext,
     remove_end,
     strip_jsonp,
     int_or_none,
     float_or_none,
     determine_ext,
     remove_end,

+    unescapeHTML,

 )
 
 
 class ORFTVthekIE(InfoExtractor):
     IE_NAME = 'orf:tvthek'
     IE_DESC = 'ORF TVthek'
 )
 
 
 class ORFTVthekIE(InfoExtractor):
     IE_NAME = 'orf:tvthek'
     IE_DESC = 'ORF TVthek'

-    _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics?/.+?|program/[^/]+)/(?P<id>\d+)'
+    _VALID_URL = r'https?://tvthek\.orf\.at/(?:[^/]+/)+(?P<id>\d+)'

 
     _TESTS = [{
         'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',
 
     _TESTS = [{
         'url': 'http://tvthek.orf.at/program/Aufgetischt/2745173/Aufgetischt-Mit-der-Steirischen-Tafelrunde/8891389',


@@ -40,37 +40,34 @@ class ORFTVthekIE(InfoExtractor):
         'skip': 'Blocked outside of Austria / Germany',
     }, {
         'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',
         'skip': 'Blocked outside of Austria / Germany',
     }, {
         'url': 'http://tvthek.orf.at/topic/Im-Wandel-der-Zeit/8002126/Best-of-Ingrid-Thurnher/7982256',

-        'playlist': [{
-            'md5': '68f543909aea49d621dfc7703a11cfaf',
-            'info_dict': {
-                'id': '7982259',
-                'ext': 'mp4',
-                'title': 'Best of Ingrid Thurnher',
-                'upload_date': '20140527',
-                'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
-            }
-        }],
+        'info_dict': {
+            'id': '7982259',
+            'ext': 'mp4',
+            'title': 'Best of Ingrid Thurnher',
+            'upload_date': '20140527',
+            'description': 'Viele Jahre war Ingrid Thurnher das "Gesicht" der ZIB 2. Vor ihrem Wechsel zur ZIB 2 im Jahr 1995 moderierte sie unter anderem "Land und Leute", "Österreich-Bild" und "Niederösterreich heute".',
+        },
+        'params': {
+            'skip_download': True,  # rtsp downloads
+        },

         '_skip': 'Blocked outside of Austria / Germany',
         '_skip': 'Blocked outside of Austria / Germany',

+    }, {
+        'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',
+        'skip_download': True,
+    }, {
+        'url': 'http://tvthek.orf.at/profile/Universum/35429',
+        'skip_download': True,

     }]
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
         webpage = self._download_webpage(url, playlist_id)
 
     }]
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
         webpage = self._download_webpage(url, playlist_id)
 

-        data_json = self._search_regex(
-            r'initializeAdworx\((.+?)\);\n', webpage, 'video info')
-        all_data = json.loads(data_json)
-
-        def get_segments(all_data):
-            for data in all_data:
-                if data['name'] in (
-                        'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM',
-                        'Tracker::EPISODE_DETAIL_PAGE_OVER_TOPIC'):
-                    return data['values']['segments']
-
-        sdata = get_segments(all_data)
-        if not sdata:
-            raise ExtractorError('Unable to extract segments')
+        data_jsb = self._parse_json(
+            self._search_regex(
+                r'<div[^>]+class=(["\']).*?VideoPlaylist.*?\1[^>]+data-jsb=(["\'])(?P<json>.+?)\2',
+                webpage, 'playlist', group='json'),
+            playlist_id, transform_source=unescapeHTML)['playlist']['videos']

 
         def quality_to_int(s):
             m = re.search('([0-9]+)', s)
 
         def quality_to_int(s):
             m = re.search('([0-9]+)', s)


@@ -79,8 +76,11 @@ class ORFTVthekIE(InfoExtractor):
             return int(m.group(1))
 
         entries = []
             return int(m.group(1))
 
         entries = []

-        for sd in sdata:
-            video_id = sd['id']
+        for sd in data_jsb:
+            video_id, title = sd.get('id'), sd.get('title')
+            if not video_id or not title:
+                continue
+            video_id = compat_str(video_id)

             formats = [{
                 'preference': -10 if fd['delivery'] == 'hls' else None,
                 'format_id': '%s-%s-%s' % (
             formats = [{
                 'preference': -10 if fd['delivery'] == 'hls' else None,
                 'format_id': '%s-%s-%s' % (


@@ -88,7 +88,7 @@ class ORFTVthekIE(InfoExtractor):
                 'url': fd['src'],
                 'protocol': fd['protocol'],
                 'quality': quality_to_int(fd['quality']),
                 'url': fd['src'],
                 'protocol': fd['protocol'],
                 'quality': quality_to_int(fd['quality']),

-            } for fd in sd['playlist_item_array']['sources']]
+            } for fd in sd['sources']]

 
             # Check for geoblocking.
             # There is a property is_geoprotection, but that's always false
 
             # Check for geoblocking.
             # There is a property is_geoprotection, but that's always false


@@ -115,14 +115,24 @@ class ORFTVthekIE(InfoExtractor):
             self._check_formats(formats, video_id)
             self._sort_formats(formats)
 
             self._check_formats(formats, video_id)
             self._sort_formats(formats)
 

-            upload_date = unified_strdate(sd['created_date'])
+            subtitles = {}
+            for sub in sd.get('subtitles', []):
+                sub_src = sub.get('src')
+                if not sub_src:
+                    continue
+                subtitles.setdefault(sub.get('lang', 'de-AT'), []).append({
+                    'url': sub_src,
+                })
+
+            upload_date = unified_strdate(sd.get('created_date'))

             entries.append({
                 '_type': 'video',
                 'id': video_id,
             entries.append({
                 '_type': 'video',
                 'id': video_id,

-                'title': sd['header'],
+                'title': title,

                 'formats': formats,
                 'formats': formats,

+                'subtitles': subtitles,

                 'description': sd.get('description'),
                 'description': sd.get('description'),

-                'duration': int(sd['duration_in_seconds']),
+                'duration': int_or_none(sd.get('duration_in_seconds')),

                 'upload_date': upload_date,
                 'thumbnail': sd.get('image_full_url'),
             })
                 'upload_date': upload_date,
                 'thumbnail': sd.get('image_full_url'),
             })


@@ -137,13 +147,16 @@ class ORFTVthekIE(InfoExtractor):
 class ORFOE1IE(InfoExtractor):
     IE_NAME = 'orf:oe1'
     IE_DESC = 'Radio Österreich 1'
 class ORFOE1IE(InfoExtractor):
     IE_NAME = 'orf:oe1'
     IE_DESC = 'Radio Österreich 1'

-    _VALID_URL = r'http://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://oe1\.orf\.at/(?:programm/|konsole\?.*?\btrack_id=)(?P<id>[0-9]+)'

 
     # Audios on ORF radio are only available for 7 days, so we can't add tests.
 
     # Audios on ORF radio are only available for 7 days, so we can't add tests.

-    _TEST = {
+    _TESTS = [{

         'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211',
         'only_matching': True,
         'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211',
         'only_matching': True,

-    }
+    }, {
+        'url': 'http://oe1.orf.at/konsole?show=ondemand&track_id=443608&load_day=/programm/konsole/tag/20160726',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         show_id = self._match_id(url)
 
     def _real_extract(self, url):
         show_id = self._match_id(url)


@@ -171,7 +184,7 @@ class ORFOE1IE(InfoExtractor):
 class ORFFM4IE(InfoExtractor):
     IE_NAME = 'orf:fm4'
     IE_DESC = 'radio FM4'
 class ORFFM4IE(InfoExtractor):
     IE_NAME = 'orf:fm4'
     IE_DESC = 'radio FM4'

-    _VALID_URL = r'http://fm4\.orf\.at/(?:7tage/?#|player/)(?P<date>[0-9]+)/(?P<show>\w+)'
+    _VALID_URL = r'https?://fm4\.orf\.at/(?:7tage/?#|player/)(?P<date>[0-9]+)/(?P<show>\w+)'

 
     _TEST = {
         'url': 'http://fm4.orf.at/player/20160110/IS/',
 
     _TEST = {
         'url': 'http://fm4.orf.at/player/20160110/IS/',


@@ -185,6 +198,7 @@ class ORFFM4IE(InfoExtractor):
             'timestamp': 1452456073,
             'upload_date': '20160110',
         },
             'timestamp': 1452456073,
             'upload_date': '20160110',
         },

+        'skip': 'Live streams on FM4 got deleted soon',

     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):


@@ -222,7 +236,7 @@ class ORFFM4IE(InfoExtractor):
 class ORFIPTVIE(InfoExtractor):
     IE_NAME = 'orf:iptv'
     IE_DESC = 'iptv.ORF.at'
 class ORFIPTVIE(InfoExtractor):
     IE_NAME = 'orf:iptv'
     IE_DESC = 'iptv.ORF.at'

-    _VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
+    _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'

 
     _TEST = {
         'url': 'http://iptv.orf.at/stories/2275236/',
 
     _TEST = {
         'url': 'http://iptv.orf.at/stories/2275236/',