Unify coding cookie

[youtube-dl] / youtube_dl / extractor / puls4.py

diff --git a/youtube_dl/extractor/puls4.py b/youtube_dl/extractor/puls4.py
index 70dedbff3e6e6e9c9dc81bf72898ec6f2e277863..1c54af0022f087788d6bb11a25639f1a184b42b8 100644 (file)
--- a/youtube_dl/extractor/puls4.py
+++ b/youtube_dl/extractor/puls4.py
@@ -1,61 +1,51 @@
-# -*- coding: utf-8 -*-
-
+# coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-
-import re
-
+from .prosiebensat1 import ProSiebenSat1BaseIE
+from ..utils import (
+    unified_strdate,
+    parse_duration,
+    compat_str,
+)
 
-class Puls4IE(InfoExtractor):
 
-    _VALID_URL = r'https?://www.puls4.com/video/.+?/play/(?P<id>[0-9]+)'
+class Puls4IE(ProSiebenSat1BaseIE):
+    _VALID_URL = r'https?://(?:www\.)?puls4\.com/(?P<id>(?:[^/]+/)*?videos/[^?#]+)'
     _TESTS = [{
-        'url': 'http://www.puls4.com/video/pro-und-contra/play/2716816',
-        'md5': '49f6a6629747eeec43cef6a46b5df81d',
+        'url': 'http://www.puls4.com/2-minuten-2-millionen/staffel-3/videos/2min2miotalk/Tobias-Homberger-von-myclubs-im-2min2miotalk-118118',
+        'md5': 'fd3c6b0903ac72c9d004f04bc6bb3e03',
         'info_dict': {
-            'id': '2716816',
-            'ext': 'mp4',
-            'title': 'Pro und Contra vom 23.02.2015'}},
-        {
-        'url': 'http://www.puls4.com/video/kult-spielfilme/play/1298106',
-        'md5': '6a48316c8903ece8dab9b9a7bf7a59ec',
-        'info_dict': {
-            'id': '1298106',
-            'ext': 'mp4',
-            'title': 'Lucky Fritz'}}
-    ]
+            'id': '118118',
+            'ext': 'flv',
+            'title': 'Tobias Homberger von myclubs im #2min2miotalk',
+            'description': 'md5:f9def7c5e8745d6026d8885487d91955',
+            'upload_date': '20160830',
+            'uploader': 'PULS_4',
+        },
+    }]
+    _TOKEN = 'puls4'
+    _SALT = '01!kaNgaiNgah1Ie4AeSha'
+    _CLIENT_NAME = ''
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        # if fsk-button
-        real_url = self._html_search_regex(r'\"fsk-button\".+?href=\"([^"]+)',
-                                           webpage, 'fsk_button', default=None)
-        if real_url:
-            webpage = self._download_webpage(real_url, video_id)
-
-        title = self._html_search_regex(
-            r'<div id="bg_brandableContent">.+?<h1>(.+?)</h1>',
-            webpage, 'title', flags=re.DOTALL)
-
-        sd_url = self._html_search_regex(
-            r'{\"url\":\"([^"]+?)\",\"hd\":false',
-            webpage, 'sd_url').replace('\\', '')
-
-        formats = [{'format_id': 'sd', 'url': sd_url, 'quality': -2}]
-
-        hd_url = self._html_search_regex(
-            r'{\"url\":\"([^"]+?)\",\"hd\":true',
-            webpage, 'hd_url', default=None)
-        if hd_url:
-            hd_url = hd_url.replace('\\', '')
-            formats.append({'format_id': 'hd', 'url': hd_url, 'quality': -1})
-
-        return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-            'ext': 'mp4'
-        }
+        path = self._match_id(url)
+        content_path = self._download_json(
+            'http://www.puls4.com/api/json-fe/page/' + path, path)['content'][0]['url']
+        media = self._download_json(
+            'http://www.puls4.com' + content_path,
+            content_path)['mediaCurrent']
+        player_content = media['playerContent']
+        info = self._extract_video_info(url, player_content['id'])
+        info.update({
+            'id': compat_str(media['objectId']),
+            'title': player_content['title'],
+            'description': media.get('description'),
+            'thumbnail': media.get('previewLink'),
+            'upload_date': unified_strdate(media.get('date')),
+            'duration': parse_duration(player_content.get('duration')),
+            'episode': player_content.get('episodePartName'),
+            'show': media.get('channel'),
+            'season_id': player_content.get('seasonId'),
+            'uploader': player_content.get('sourceCompany'),
+        })
+        return info