debian/control: Canonicalize with `wrap-and-sort -s -a -b`.

[youtubedl] / youtube_dl / extractor / sixplay.py

diff --git a/youtube_dl/extractor/sixplay.py b/youtube_dl/extractor/sixplay.py
index d3aba58a29a981829d0562ee56d992fc49f2f67c..1f8469a90876673a21cbd3d436fde3081c3e015c 100644 (file)
--- a/youtube_dl/extractor/sixplay.py
+++ b/youtube_dl/extractor/sixplay.py
@@ -1,64 +1,119 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import (
+    compat_parse_qs,
+    compat_str,
+    compat_urllib_parse_urlparse,
+)

 from ..utils import (
 from ..utils import (

-    qualities,
-    int_or_none,
-    mimetype2ext,

     determine_ext,
     determine_ext,

+    int_or_none,
+    try_get,
+    qualities,

 )
 
 
 class SixPlayIE(InfoExtractor):
 )
 
 
 class SixPlayIE(InfoExtractor):

-    _VALID_URL = r'(?:6play:|https?://(?:www\.)?6play\.fr/.+?-c_)(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.6play.fr/jamel-et-ses-amis-au-marrakech-du-rire-p_1316/jamel-et-ses-amis-au-marrakech-du-rire-2015-c_11495320',
-        'md5': '42310bffe4ba3982db112b9cd3467328',
+    IE_NAME = '6play'
+    _VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay.be)/.+?-c_)(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
+        'md5': '31fcd112637baa0c2ab92c4fcd8baf27',

         'info_dict': {
         'info_dict': {

-            'id': '11495320',
+            'id': '12041051',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Jamel et ses amis au Marrakech du rire 2015',
-            'description': 'md5:ba2149d5c321d5201b78070ee839d872',
+            'title': 'Le but qui a marqué l\'histoire du football français !',
+            'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851',

         },
         },

-    }
+    }, {
+        'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
+        'only_matching': True,
+    }]

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

-        video_id = self._match_id(url)
-        clip_data = self._download_json(
-            'https://player.m6web.fr/v2/video/config/6play-auth/FR/%s.json' % video_id,
-            video_id)
-        video_data = clip_data['videoInfo']
+        domain, video_id = re.search(self._VALID_URL, url).groups()
+        service, consumer_name = {
+            '6play.fr': ('6play', 'm6web'),
+            'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
+        }.get(domain, ('6play', 'm6web'))
+
+        data = self._download_json(
+            'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/%s/videos/clip_%s' % (service, video_id),
+            video_id, headers={
+                'x-customer-name': consumer_name
+            }, query={
+                'csa': 5,
+                'with': 'clips',
+            })
+
+        clip_data = data['clips'][0]
+        title = clip_data['title']

 
 

+        urls = []

         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
         formats = []
         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
         formats = []

-        for source in clip_data['sources']:
-            source_type, source_url = source.get('type'), source.get('src')
-            if not source_url or source_type == 'hls/primetime':
+        subtitles = {}
+        for asset in clip_data['assets']:
+            asset_url = asset.get('full_physical_path')
+            protocol = asset.get('protocol')
+            if not asset_url or protocol == 'primetime' or asset_url in urls:

                 continue
                 continue

-            ext = mimetype2ext(source_type) or determine_ext(source_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    source_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id='hls', fatal=False))
-                formats.extend(self._extract_f4m_formats(
-                    source_url.replace('.m3u8', '.f4m'),
-                    video_id, f4m_id='hds', fatal=False))
-            elif ext == 'mp4':
-                quality = source.get('quality')
+            urls.append(asset_url)
+            container = asset.get('video_container')
+            ext = determine_ext(asset_url)
+            if protocol == 'http_subtitle' or ext == 'vtt':
+                subtitles.setdefault('fr', []).append({'url': asset_url})
+                continue
+            if container == 'm3u8' or ext == 'm3u8':
+                if protocol == 'usp':
+                    if compat_parse_qs(compat_urllib_parse_urlparse(asset_url).query).get('token', [None])[0]:
+                        urlh = self._request_webpage(asset_url, video_id, fatal=False)
+                        if not urlh:
+                            continue
+                        asset_url = urlh.geturl()
+                    asset_url = re.sub(r'/([^/]+)\.ism/[^/]*\.m3u8', r'/\1.ism/\1.m3u8', asset_url)
+                    formats.extend(self._extract_m3u8_formats(
+                        asset_url, video_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+                    formats.extend(self._extract_f4m_formats(
+                        asset_url.replace('.m3u8', '.f4m'),
+                        video_id, f4m_id='hds', fatal=False))
+                    formats.extend(self._extract_mpd_formats(
+                        asset_url.replace('.m3u8', '.mpd'),
+                        video_id, mpd_id='dash', fatal=False))
+                    formats.extend(self._extract_ism_formats(
+                        re.sub(r'/[^/]+\.m3u8', '/Manifest', asset_url),
+                        video_id, ism_id='mss', fatal=False))
+                else:
+                    formats.extend(self._extract_m3u8_formats(
+                        asset_url, video_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False))
+            elif container == 'mp4' or ext == 'mp4':
+                quality = asset.get('video_quality')

                 formats.append({
                 formats.append({

-                    'url': source_url,
+                    'url': asset_url,

                     'format_id': quality,
                     'quality': quality_key(quality),
                     'ext': ext,
                 })
         self._sort_formats(formats)
 
                     'format_id': quality,
                     'quality': quality_key(quality),
                     'ext': ext,
                 })
         self._sort_formats(formats)
 

+        def get(getter):
+            for src in (data, clip_data):
+                v = try_get(src, getter, compat_str)
+                if v:
+                    return v
+

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

-            'title': video_data['title'].strip(),
-            'description': video_data.get('description'),
-            'duration': int_or_none(video_data.get('duration')),
-            'series': video_data.get('titlePgm'),
+            'title': title,
+            'description': get(lambda x: x['description']),
+            'duration': int_or_none(clip_data.get('duration')),
+            'series': get(lambda x: x['program']['title']),

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

+            'subtitles': subtitles,

         }
         }