[nowtv] Improve and simplify

youtube_dl/extractor/__init__.py

@@ -355,7 +355,7 @@ from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
-from .nowtv import NowTvIE
+from .nowtv import NowTVIE
 from .nowvideo import NowVideoIE
 from .npo import (
     NPOIE,

youtube_dl/extractor/nowtv.py

@@ -1,90 +1,169 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
-    qualities,
-    unified_strdate,
     int_or_none,
+    parse_iso8601,
+    parse_duration,
+    remove_start,
 )
 
-class NowTvIE(InfoExtractor):
-    """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
-    _VALID_URL = r'''(?x)
-                        (?:https?://)?
-                        (
-                            (?:www\.)?nowtv\.de
-                            /(rtl|rtl2|rtlnitro||superrtl|ntv|vox)(?P<path>/.*?)/player
-                        )'''
 
-    _TESTS = [
+class NowTVIE(InfoExtractor):
-        {
+    _VALID_URL = r'https?://(?:www\.)?nowtv\.de/(?P<station>rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<id>.+?)/player'
-            'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player',
+
-            'info_dict': {
+    _TESTS = [{
-                'id': '128953',
+        # rtl
-                'ext': 'mp4',
+        'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player',
-                'title': 'B\u00fcro-Fall \/ Chihuahua \'Joel\'',
+        'info_dict': {
-                'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de',
+            'id': '203519',
-                'upload_date': '2015-05-23 19:10:00',
+            'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit',
-                'duration': '00:51:32',
+            'ext': 'mp4',
-            },
+            'title': 'Die neuen Bauern und eine Hochzeit',
-            'params': {
+            'description': 'md5:e234e1ed6d63cf06be5c070442612e7e',
-                'skip_download': True,
+            'thumbnail': 're:^https?://.*\.jpg$',
-            },
+            'timestamp': 1432580700,
-            'skip': 'Only works from Germany',
+            'upload_date': '20150525',
+            'duration': 2786,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # rtl2
+        'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player',
+        'info_dict': {
+            'id': '203481',
+            'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934',
+            'ext': 'mp4',
+            'title': 'Berlin - Tag & Nacht (Folge 934)',
+            'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432666800,
+            'upload_date': '20150526',
+            'duration': 2641,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # superrtl
+        'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player',
+        'info_dict': {
+            'id': '99205',
+            'display_id': 'medicopter-117/angst',
+            'ext': 'mp4',
+            'title': 'Angst!',
+            'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1222632900,
+            'upload_date': '20080928',
+            'duration': 3025,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # ntv
+        'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player',
+        'info_dict': {
+            'id': '203521',
+            'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch',
+            'ext': 'mp4',
+            'title': 'Thema u.a.: Der erste Blick: Die Apple Watch',
+            'description': 'md5:4312b6c9d839ffe7d8caf03865a531af',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432751700,
+            'upload_date': '20150527',
+            'duration': 1083,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # vox
+        'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player',
+        'info_dict': {
+            'id': '128953',
+            'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel',
+            'ext': 'mp4',
+            'title': "Büro-Fall / Chihuahua 'Joel'",
+            'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1432408200,
+            'upload_date': '20150523',
+            'duration': 3092,
         },
-    ]
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        info_url = 'https://api.nowtv.de/v3/movies' + mobj.group('path') + '?fields=*,format,files,breakpoints,paymentPaytypes,trailers'
+        display_id = mobj.group('id')
-        info = self._download_json(info_url, None)
+        station = mobj.group('station')
 
-        video_id = info['id']
+        info = self._download_json(
-        title = info['title']
+            'https://api.nowtv.de/v3/movies/%s?fields=*,format,files,breakpoints,paymentPaytypes,trailers,pictures' % display_id,
-        description = info['articleShort']
+            display_id)
-        duration = info['duration']
+
-        upload_date = unified_strdate(info['broadcastStartDate'])
+        video_id = compat_str(info['id'])
-        free = info['free']
-        station = info['format']['station']
-        thumbnail = info['format']['defaultImage169Logo']
 
-        if station == 'rtl':
+        if info.get('geoblocked'):
-            base_url = 'http://hls.fra.rtlnow.de/hls-vod-enc/'
+            raise ExtractorError(
-        elif station == 'rtl2':
+                'Video %s is not available from your location due to geo restriction' % video_id,
-            base_url = 'http://hls.fra.rtl2now.de/hls-vod-enc/'
+                expected=True)
-        elif station == 'vox':
+
-            base_url = 'http://hls.fra.voxnow.de/hls-vod-enc/'
+        f = info.get('format', {})
-        elif station == 'nitro':
+        station = f.get('station') or station
-            base_url = 'http://hls.fra.rtlnitronow.de/hls-vod-enc/'
+
-        elif station == 'ntv':
+        STATIONS = {
-            base_url = 'http://hls.fra.n-tvnow.de/hls-vod-enc/'
+            'rtl': 'rtlnow',
-        elif station == 'superrtl':
+            'rtl2': 'rtl2now',
-            base_url = 'http://hls.fra.superrtlnow.de/hls-vod-enc/'
+            'vox': 'voxnow',
+            'nitro': 'rtlnitronow',
+            'ntv': 'n-tvnow',
+            'superrtl': 'superrtlnow'
+        }
 
         formats = []
         for item in info['files']['items']:
-            if item['type'] != 'video/x-abr':
+            item_path = remove_start(item['path'], '/')
-                continue
+            tbr = int_or_none(item['bitrate'])
-
+            m3u8_url = 'http://hls.fra.%s.de/hls-vod-enc/%s.m3u8' % (STATIONS[station], item_path)
-            fmt = {
+            m3u8_url = m3u8_url.replace('now/', 'now/videos/')
-                'url': base_url + item['path'] + '.m3u8',
+            formats.append({
-                'tbr': int_or_none(item['bitrate']),
+                'url': m3u8_url,
+                'format_id': '%s-%sk' % (item['id'], tbr),
                 'ext': 'mp4',
-                'format_id': int_or_none(item['id']),
+                'tbr': tbr,
-            }
+            })
-            formats.append(fmt)
         self._sort_formats(formats)
 
+        title = info['title']
+        description = info.get('articleLong') or info.get('articleShort')
+        timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ')
+        duration = parse_duration(info.get('duration'))
+        thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo')
+
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,
-            'upload_date': upload_date,
+            'timestamp': timestamp,
             'duration': duration,
             'formats': formats,
         }