Use canonical URL in Vcs-Git.

[youtubedl] / youtube_dl / extractor / orf.py

diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py
index cc296eabd9db93bf3106e4c9bf427ad4abe645c9..d54b8ace6e5eeee6ee7188bd1cfe88a2471f3627 100644 (file)
--- a/youtube_dl/extractor/orf.py
+++ b/youtube_dl/extractor/orf.py
@@ -6,14 +6,18 @@ import re
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (

+    clean_html,
+    determine_ext,
+    float_or_none,

     HEADRequest,
     HEADRequest,

-    unified_strdate,
-    strip_jsonp,

     int_or_none,
     int_or_none,

-    float_or_none,
-    determine_ext,
+    orderedSet,

     remove_end,
     remove_end,

+    str_or_none,
+    strip_jsonp,

     unescapeHTML,
     unescapeHTML,

+    unified_strdate,
+    url_or_none,

 )
 
 
 )
 
 


@@ -48,13 +52,13 @@ class ORFTVthekIE(InfoExtractor):
         'params': {
             'skip_download': True,  # rtsp downloads
         },
         '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',
     }, {
         'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141',

-        'skip_download': True,
+        'only_matching': True,

     }, {
         'url': 'http://tvthek.orf.at/profile/Universum/35429',
     }, {
         'url': 'http://tvthek.orf.at/profile/Universum/35429',

-        'skip_download': True,
+        'only_matching': True,

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


@@ -67,26 +71,39 @@ class ORFTVthekIE(InfoExtractor):
                 webpage, 'playlist', group='json'),
             playlist_id, transform_source=unescapeHTML)['playlist']['videos']
 
                 webpage, 'playlist', group='json'),
             playlist_id, transform_source=unescapeHTML)['playlist']['videos']
 

-        def quality_to_int(s):
-            m = re.search('([0-9]+)', s)
-            if m is None:
-                return -1
-            return int(m.group(1))
-

         entries = []
         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)
         entries = []
         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' % (
-                    fd['delivery'], fd['quality'], fd['quality_string']),
-                'url': fd['src'],
-                'protocol': fd['protocol'],
-                'quality': quality_to_int(fd['quality']),
-            } for fd in sd['sources']]
+            formats = []
+            for fd in sd['sources']:
+                src = url_or_none(fd.get('src'))
+                if not src:
+                    continue
+                format_id_list = []
+                for key in ('delivery', 'quality', 'quality_string'):
+                    value = fd.get(key)
+                    if value:
+                        format_id_list.append(value)
+                format_id = '-'.join(format_id_list)
+                ext = determine_ext(src)
+                if ext == 'm3u8':
+                    m3u8_formats = self._extract_m3u8_formats(
+                        src, video_id, 'mp4', m3u8_id=format_id, fatal=False)
+                    if any('/geoprotection' in f['url'] for f in m3u8_formats):
+                        self.raise_geo_restricted()
+                    formats.extend(m3u8_formats)
+                elif ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        src, video_id, f4m_id=format_id, fatal=False))
+                else:
+                    formats.append({
+                        'format_id': format_id,
+                        'url': src,
+                        'protocol': fd.get('protocol'),
+                    })

 
             # 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


@@ -149,43 +166,48 @@ class ORFRadioIE(InfoExtractor):
         show_date = mobj.group('date')
         show_id = mobj.group('show')
 
         show_date = mobj.group('date')
         show_id = mobj.group('show')
 

-        if station == 'fm4':
-            show_id = '4%s' % show_id
-

         data = self._download_json(
         data = self._download_json(

-            'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date),
-            show_id
-        )
-
-        def extract_entry_dict(info, title, subtitle):
-            return {
-                'id': info['loopStreamId'].replace('.mp3', ''),
-                'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']),
-                'title': title,
-                'description': subtitle,
-                'duration': (info['end'] - info['start']) / 1000,
-                'timestamp': info['start'] / 1000,
-                'ext': 'mp3'
-            }
+            'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
+            % (station, show_id, show_date), show_id)

 
 

-        entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
+        entries = []
+        for info in data['streams']:
+            loop_stream_id = str_or_none(info.get('loopStreamId'))
+            if not loop_stream_id:
+                continue
+            title = str_or_none(data.get('title'))
+            if not title:
+                continue
+            start = int_or_none(info.get('start'), scale=1000)
+            end = int_or_none(info.get('end'), scale=1000)
+            duration = end - start if end and start else None
+            entries.append({
+                'id': loop_stream_id.replace('.mp3', ''),
+                'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, loop_stream_id),
+                'title': title,
+                'description': clean_html(data.get('subtitle')),
+                'duration': duration,
+                'timestamp': start,
+                'ext': 'mp3',
+                'series': data.get('programTitle'),
+            })

 
         return {
             '_type': 'playlist',
             'id': show_id,
 
         return {
             '_type': 'playlist',
             'id': show_id,

-            'title': data['title'],
-            'description': data['subtitle'],
-            'entries': entries
+            'title': data.get('title'),
+            'description': clean_html(data.get('subtitle')),
+            'entries': entries,

         }
 
 
 class ORFFM4IE(ORFRadioIE):
     IE_NAME = 'orf:fm4'
     IE_DESC = 'radio FM4'
         }
 
 
 class ORFFM4IE(ORFRadioIE):
     IE_NAME = 'orf:fm4'
     IE_DESC = 'radio FM4'

-    _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>\w+)'
+    _VALID_URL = r'https?://(?P<station>fm4)\.orf\.at/player/(?P<date>[0-9]+)/(?P<show>4\w+)'

 
     _TEST = {
 
     _TEST = {

-        'url': 'http://fm4.orf.at/player/20170107/CC',
+        'url': 'http://fm4.orf.at/player/20170107/4CC',

         'md5': '2b0be47375432a7ef104453432a19212',
         'info_dict': {
             'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',
         'md5': '2b0be47375432a7ef104453432a19212',
         'info_dict': {
             'id': '2017-01-07_2100_tl_54_7DaysSat18_31295',


@@ -196,7 +218,8 @@ class ORFFM4IE(ORFRadioIE):
             'timestamp': 1483819257,
             'upload_date': '20170107',
         },
             'timestamp': 1483819257,
             'upload_date': '20170107',
         },

-        'skip': 'Shows from ORF radios are only available for 7 days.'
+        'skip': 'Shows from ORF radios are only available for 7 days.',
+        'only_matching': True,

     }
 
 
     }
 
 


@@ -307,3 +330,108 @@ class ORFIPTVIE(InfoExtractor):
             'upload_date': upload_date,
             'formats': formats,
         }
             'upload_date': upload_date,
             'formats': formats,
         }

+
+
+class ORFFM4StoryIE(InfoExtractor):
+    IE_NAME = 'orf:fm4:story'
+    IE_DESC = 'fm4.orf.at stories'
+    _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://fm4.orf.at/stories/2865738/',
+        'playlist': [{
+            'md5': 'e1c2c706c45c7b34cf478bbf409907ca',
+            'info_dict': {
+                'id': '547792',
+                'ext': 'flv',
+                'title': 'Manu Delago und Inner Tongue live',
+                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
+                'duration': 1748.52,
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'upload_date': '20170913',
+            },
+        }, {
+            'md5': 'c6dd2179731f86f4f55a7b49899d515f',
+            'info_dict': {
+                'id': '547798',
+                'ext': 'flv',
+                'title': 'Manu Delago und Inner Tongue live (2)',
+                'duration': 1504.08,
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'upload_date': '20170913',
+                'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.',
+            },
+        }],
+    }
+
+    def _real_extract(self, url):
+        story_id = self._match_id(url)
+        webpage = self._download_webpage(url, story_id)
+
+        entries = []
+        all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage))
+        for idx, video_id in enumerate(all_ids):
+            data = self._download_json(
+                'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id,
+                video_id)[0]
+
+            duration = float_or_none(data['duration'], 1000)
+
+            video = data['sources']['q8c']
+            load_balancer_url = video['loadBalancerUrl']
+            abr = int_or_none(video.get('audioBitrate'))
+            vbr = int_or_none(video.get('bitrate'))
+            fps = int_or_none(video.get('videoFps'))
+            width = int_or_none(video.get('videoWidth'))
+            height = int_or_none(video.get('videoHeight'))
+            thumbnail = video.get('preview')
+
+            rendition = self._download_json(
+                load_balancer_url, video_id, transform_source=strip_jsonp)
+
+            f = {
+                'abr': abr,
+                'vbr': vbr,
+                'fps': fps,
+                'width': width,
+                'height': height,
+            }
+
+            formats = []
+            for format_id, format_url in rendition['redirect'].items():
+                if format_id == 'rtmp':
+                    ff = f.copy()
+                    ff.update({
+                        'url': format_url,
+                        'format_id': format_id,
+                    })
+                    formats.append(ff)
+                elif determine_ext(format_url) == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url, video_id, f4m_id=format_id))
+                elif determine_ext(format_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, video_id, 'mp4', m3u8_id=format_id))
+                else:
+                    continue
+            self._sort_formats(formats)
+
+            title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at')
+            if idx >= 1:
+                # Titles are duplicates, make them unique
+                title += ' (' + str(idx + 1) + ')'
+            description = self._og_search_description(webpage)
+            upload_date = unified_strdate(self._html_search_meta(
+                'dc.date', webpage, 'upload date'))
+
+            entries.append({
+                'id': video_id,
+                'title': title,
+                'description': description,
+                'duration': duration,
+                'thumbnail': thumbnail,
+                'upload_date': upload_date,
+                'formats': formats,
+            })
+
+        return self.playlist_result(entries)