youtube-dl

commit cd9ff4ec5be86b4a16afc792ff9cf0d5c3eacd47
parent c6c6a64aa58af54d3f1d4ebdd21547e708b29bf6
Author: Remita Amine <remitamine@gmail.com>
Date:   Fri, 24 Nov 2017 20:00:01 +0100

[massengeschmacktv] Add support for Massengeschmack TV(replaces Fernseh Kritik TV)

Diffstat:
M
youtube_dl/extractor/extractors.py
 | 
2
+-
D
youtube_dl/extractor/fktv.py
 | 
51
---------------------------------------------------
A
youtube_dl/extractor/massengeschmacktv.py
 | 
77
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

3 files changed, 78 insertions(+), 52 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -348,7 +348,6 @@ from .firstpost import FirstpostIE
 from .firsttv import FirstTVIE
 from .fivemin import FiveMinIE
 from .fivetv import FiveTVIE
-from .fktv import FKTVIE
 from .flickr import FlickrIE
 from .flipagram import FlipagramIE
 from .folketinget import FolketingetIE
@@ -572,6 +571,7 @@ from .mangomolo import (
     MangomoloLiveIE,
 )
 from .manyvids import ManyVidsIE
+from .massengeschmacktv import MassengeschmackTVIE
 from .matchtv import MatchTVIE
 from .mdr import MDRIE
 from .mediaset import MediasetIE
diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py
@@ -1,51 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    determine_ext,
-    js_to_json,
-)
-
-
-class FKTVIE(InfoExtractor):
-    IE_NAME = 'fernsehkritik.tv'
-    _VALID_URL = r'https?://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
-
-    _TEST = {
-        'url': 'http://fernsehkritik.tv/folge-1',
-        'md5': '21f0b0c99bce7d5b524eb1b17b1c6d79',
-        'info_dict': {
-            'id': '1',
-            'ext': 'mp4',
-            'title': 'Folge 1 vom 10. April 2007',
-            'thumbnail': r're:^https?://.*\.jpg$',
-        },
-    }
-
-    def _real_extract(self, url):
-        episode = self._match_id(url)
-
-        webpage = self._download_webpage(
-            'http://fernsehkritik.tv/folge-%s/play' % episode, episode)
-        title = clean_html(self._html_search_regex(
-            '<h3>([^<]+)</h3>', webpage, 'title'))
-        thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
-        sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
-
-        formats = []
-        for source in sources:
-            furl = source.get('src')
-            if furl:
-                formats.append({
-                    'url': furl,
-                    'format_id': determine_ext(furl),
-                })
-        self._sort_formats(formats)
-
-        return {
-            'id': episode,
-            'title': title,
-            'formats': formats,
-            'thumbnail': thumbnail,
-        }
diff --git a/youtube_dl/extractor/massengeschmacktv.py b/youtube_dl/extractor/massengeschmacktv.py
@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    mimetype2ext,
+    parse_filesize,
+)
+
+
+class MassengeschmackTVIE(InfoExtractor):
+    IE_NAME = 'massengeschmack.tv'
+    _VALID_URL = r'https?://(?:www\.)?massengeschmack\.tv/play/(?P<id>[^?&#]+)'
+
+    _TEST = {
+        'url': 'https://massengeschmack.tv/play/fktv202',
+        'md5': 'a9e054db9c2b5a08f0a0527cc201e8d3',
+        'info_dict': {
+            'id': 'fktv202',
+            'ext': 'mp4',
+            'title': 'Fernsehkritik-TV - Folge 202',
+        },
+    }
+
+    def _real_extract(self, url):
+        episode = self._match_id(url)
+
+        webpage = self._download_webpage(url, episode)
+        title = clean_html(self._html_search_regex(
+            '<h3>([^<]+)</h3>', webpage, 'title'))
+        thumbnail = self._search_regex(r'POSTER\s*=\s*"([^"]+)', webpage, 'thumbnail', fatal=False)
+        sources = self._parse_json(self._search_regex(r'(?s)MEDIA\s*=\s*(\[.+?\]);', webpage, 'media'), episode, js_to_json)
+
+        formats = []
+        for source in sources:
+            furl = source.get('src')
+            if not furl:
+                continue
+            furl = self._proto_relative_url(furl)
+            ext = determine_ext(furl) or mimetype2ext(source.get('type'))
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    furl, episode, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'url': furl,
+                    'format_id': determine_ext(furl),
+                })
+
+        for (durl, format_id, width, height, filesize) in re.findall(r'''(?x)
+                                   <a[^>]+?href="(?P<url>(?:https:)?//[^"]+)".*?
+                                   <strong>(?P<format_id>.+?)</strong>.*?
+                                   <small>(?:(?P<width>\d+)x(?P<height>\d+))?\s+?\((?P<filesize>[\d,]+\s*[GM]iB)\)</small>
+                                ''', webpage):
+            formats.append({
+                'url': durl,
+                'format_id': format_id,
+                'width': int_or_none(width),
+                'height': int_or_none(height),
+                'filesize': parse_filesize(filesize),
+                'vcodec': 'none' if format_id.startswith('Audio') else None,
+            })
+
+        self._sort_formats(formats, ('width', 'height', 'filesize', 'tbr'))
+
+        return {
+            'id': episode,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }