[hors-serie] Add new extractor

youtube_dl/extractor/extractors.py

@@ -69,7 +69,10 @@ from .arte import (
     TheOperaPlatformIE,
     ArteTVPlaylistIE,
 )
-from .loubiana import ArretSurImagesIE
+from .loubiana import (
+    ArretSurImagesIE,
+    HorsSerieIE,
+)
 from .atresplayer import AtresPlayerIE
 from .atttechchannel import ATTTechChannelIE
 from .audimedia import AudiMediaIE

youtube_dl/extractor/loubiana.py

@@ -13,6 +13,9 @@ from ..utils import (
 class ArretSurImagesIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?arretsurimages\.net/emissions/.*?-id(?P<id>[0-9]+)'
     _LOGIN_URL = 'https://www.arretsurimages.net/forum/login.php'
+    _DOWNLOAD_URL = 'https?://v42.arretsurimages.net'
+    _FILE_URL = 'https?://v42.arretsurimages.net/fichiers'
+
     _TEST = {
         'url': 'https://www.arretsurimages.net/emissions/2017-02-17/Theo-La-matraque-telescopique-beaucoup-de-collegues-l-ont-demandee-id9557',
         'md5': '650d2102dad67b2b6a94ac9c063f6d5b',
@@ -32,36 +35,42 @@ class ArretSurImagesIE(InfoExtractor):
         if username is None:
             return
 
-        login_data = urlencode_postdata({
+        login_data = urlencode_postdata(self._get_login_data(username, password))
-            'ok': 'Valider',
-            'username': username,
-            'password': password,
-        });
 
         login_results = self._download_webpage(
             sanitized_Request(self._LOGIN_URL, login_data),
             None, note='Logging in', errnote='Unable to log in')
 
-        if re.search(r'(?i)Ce nom d\'utilisateur / mot de passe est introuvable ou inactif. Recommencez', login_results) is not None:
+        if not self._is_logged(login_results):
             self._downloader.report_warning('unable to log in: bad username or password')
             return False
 
         return True
 
+    def _is_logged(self, login_results):
+        return re.search(r'(?i)Ce nom d\'utilisateur / mot de passe est introuvable ou inactif. Recommencez', login_results) is None
+
+    def _get_login_data(self, username, password):
+        return {
+            'ok': 'Valider',
+            'username': username,
+            'password': password,
+        }
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         video_title = self._html_search_regex(
-            r'<h1 itemprop="headline">(.*?)</h1>',
+            r'<h1 itemprop=".*?">(.*?)</h1>',
             webpage, 'title')
         download_url = self._html_search_regex(
-            r'<a href="(http://v42.arretsurimages.net/telecharger/.*?.mp4)" target="_blank" class="bouton-telecharger"></a>',
+            r'<a href="(' + self._DOWNLOAD_URL + '/telecharger/.*?.mp4)"',
             webpage, 'download information')
 
         download_page = self._download_webpage(download_url, video_id, 'Downloading download information page')
         video_url = self._html_search_regex(
-            r'<a id="file" href="(http://v42.arretsurimages.net/fichiers/.*?.mp4)" download>suivre ce lien</a>',
+            r'<a id="file" href="(' + self._FILE_URL + '/.*?.mp4)" download>suivre ce lien</a>',
             download_page, 'video url')
 
         return {
@@ -69,3 +78,31 @@ class ArretSurImagesIE(InfoExtractor):
             'title': video_title,
             'url': video_url,
         }
+
+
+class HorsSerieIE(ArretSurImagesIE):
+    _VALID_URL = r'https?://(?:www\.)?hors-serie\.net/.*?-id(?P<id>[0-9]+)'
+    _LOGIN_URL = 'https://www.hors-serie.net/connexion.php'
+    _DOWNLOAD_URL = 'https?://v42.hors-serie.net'
+    _FILE_URL = 'https?://v42.hors-serie.net/fichiers_hs'
+
+    _TEST = {
+        'url': 'http://www.hors-serie.net/Dans-le-Texte/2017-01-21/L-effondrement-qui-vient-id211',
+        'md5': 'a6aabfe23871146fb55c924e196680c2',
+        'info_dict': {
+            'id': '211',
+            'ext': 'mp4',
+            'title': 'L\'effondrement qui vient',
+        },
+        'skip': 'Requires account credentials',
+    }
+
+    def _get_login_data(self, username, password):
+        return {
+            'submit': 'valider',
+            'mail': username,
+            'pass': password,
+        }
+
+    def _is_logged(self, login_results):
+        return re.search(r'(?i)Adresse électronique ou mot de passe invalide...', login_results) is None