[generic] Add test for Senate ISVP iframe embed

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

diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index 84aa1258541dabd6da12ceb077eee25ca5a7453c..58ffde541451bbaf863a82a0bb0986d27a8fcf4f 100644 (file)
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import compat_chr
 from ..utils import (
@@ -10,7 +12,7 @@ from ..utils import (
 
 
 class OpenloadIE(InfoExtractor):
-    _VALID_URL = r'https?://openload\.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
+    _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
 
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
@@ -19,7 +21,7 @@ class OpenloadIE(InfoExtractor):
             'id': 'kUEfGclsU9o',
             'ext': 'mp4',
             'title': 'skyrim_no-audio_1080.mp4',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         },
     }, {
         'url': 'https://openload.co/embed/rjC09fkPLYs',
@@ -27,7 +29,7 @@ class OpenloadIE(InfoExtractor):
             'id': 'rjC09fkPLYs',
             'ext': 'mp4',
             'title': 'movie.mp4',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'subtitles': {
                 'en': [{
                     'ext': 'vtt',
@@ -51,8 +53,17 @@ class OpenloadIE(InfoExtractor):
         # for title and ext
         'url': 'https://openload.co/embed/Sxz5sADo82g/',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
+        'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
+            webpage)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
@@ -61,19 +72,54 @@ class OpenloadIE(InfoExtractor):
             raise ExtractorError('File not found', expected=True)
 
         ol_id = self._search_regex(
-            '<span[^>]+id="[a-zA-Z0-9]+x"[^>]*>([0-9]+)</span>',
+            '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
             webpage, 'openload ID')
 
-        first_two_chars = int(float(ol_id[0:][:2]))
-        urlcode = ''
-        num = 2
+        video_url_chars = []
+
+        first_char = ord(ol_id[0])
+        key = first_char - 55
+        maxKey = max(2, key)
+        key = min(maxKey, len(ol_id) - 38)
+        t = ol_id[key:key + 36]
+
+        hashMap = {}
+        v = ol_id.replace(t, '')
+        h = 0
+
+        while h < len(t):
+            f = t[h:h + 3]
+            i = int(f, 8)
+            hashMap[h / 3] = i
+            h += 3
+
+        h = 0
+        H = 0
+        while h < len(v):
+            B = ''
+            C = ''
+            if len(v) >= h + 2:
+                B = v[h:h + 2]
+            if len(v) >= h + 3:
+                C = v[h:h + 3]
+            i = int(B, 16)
+            h += 2
+            if H % 3 == 0:
+                i = int(C, 8)
+                h += 1
+            elif H % 2 == 0 and H != 0 and ord(v[H - 1]) < 60:
+                i = int(C, 10)
+                h += 1
+            index = H % 7
 
-        while num < len(ol_id):
-            urlcode += compat_chr(int(float(ol_id[num:][:3])) -
-                                  first_two_chars * int(float(ol_id[num + 3:][:2])))
-            num += 5
+            A = hashMap[index]
+            i ^= 213
+            i ^= A
+            video_url_chars.append(compat_chr(i))
+            H += 1
 
-        video_url = 'https://openload.co/stream/' + urlcode
+        video_url = 'https://openload.co/stream/%s?mime=true'
+        video_url = video_url % (''.join(video_url_chars))
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@@ -89,7 +135,7 @@ class OpenloadIE(InfoExtractor):
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
             # Seems all videos have extensions in their titles
-            'ext': determine_ext(title),
+            'ext': determine_ext(title, 'mp4'),
             'subtitles': subtitles,
         }
         return info_dict