Prepare for upload.

[youtubedl] / youtube_dl / extractor / eroprofile.py

diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py
index 79e2fbd394681283e07a7146bc51f39a7499324d..7fcd0151d8efdfd2b2378c0097b363e563e3171b 100644 (file)
--- a/youtube_dl/extractor/eroprofile.py
+++ b/youtube_dl/extractor/eroprofile.py
@@ -1,11 +1,20 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import compat_urllib_parse
+from ..utils import (
+    ExtractorError,
+    unescapeHTML
+)

 
 
 class EroProfileIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
 
 
 class EroProfileIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'

-    _TEST = {
+    _LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
+    _NETRC_MACHINE = 'eroprofile'
+    _TESTS = [{

         'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
         'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
         'info_dict': {
         'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
         'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
         'info_dict': {


@@ -16,19 +25,60 @@ class EroProfileIE(InfoExtractor):
             'thumbnail': 're:https?://.*\.jpg',
             'age_limit': 18,
         }
             'thumbnail': 're:https?://.*\.jpg',
             'age_limit': 18,
         }

-    }
+    }, {
+        'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
+        'md5': '1baa9602ede46ce904c431f5418d8916',
+        'info_dict': {
+            'id': '1133519',
+            'ext': 'm4v',
+            'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
+            'thumbnail': 're:https?://.*\.jpg',
+            'age_limit': 18,
+        },
+        'skip': 'Requires login',
+    }]
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        query = compat_urllib_parse.urlencode({
+            'username': username,
+            'password': password,
+            'url': 'http://www.eroprofile.com/',
+        })
+        login_url = self._LOGIN_URL + query
+        login_page = self._download_webpage(login_url, None, False)
+
+        m = re.search(r'Your username or password was incorrect\.', login_page)
+        if m:
+            raise ExtractorError(
+                'Wrong username and/or password.', expected=True)
+
+        self.report_login()
+        redirect_url = self._search_regex(
+            r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
+        self._download_webpage(redirect_url, None, False)
+
+    def _real_initialize(self):
+        self._login()

 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
 

+        m = re.search(r'You must be logged in to view this video\.', webpage)
+        if m:
+            self.raise_login_required('This video requires login')
+

         video_id = self._search_regex(
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
             webpage, 'video id', default=None)
 
         video_id = self._search_regex(
             [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
             webpage, 'video id', default=None)
 

-        video_url = self._search_regex(
-            r'<source src="([^"]+)', webpage, 'video url')
+        video_url = unescapeHTML(self._search_regex(
+            r'<source src="([^"]+)', webpage, 'video url'))

         title = self._html_search_regex(
             r'Title:</th><td>([^<]+)</td>', webpage, 'title')
         thumbnail = self._search_regex(
         title = self._html_search_regex(
             r'Title:</th><td>([^<]+)</td>', webpage, 'title')
         thumbnail = self._search_regex(