Merge branch 'master' into openload-phantomjs-method

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

diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index 435aec28e2fbf20e29399c12281ff7d7c6a9fa3f..292476ef86cf8680fc59e58488f84cae44da7947 100644 (file)
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -4,10 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_chr
 from ..utils import (
     determine_ext,
     ExtractorError,
+    get_element_by_id,
+    PhantomJSwrapper,
 )
 
 
@@ -58,6 +59,8 @@ class OpenloadIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
+
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
@@ -66,60 +69,22 @@ class OpenloadIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
+        url = 'https://openload.co/embed/%s/' % video_id
+        headers = {
+            'User-Agent': self._USER_AGENT,
+        }
+
+        webpage = self._download_webpage(url, video_id, headers=headers)
 
         if 'File not found' in webpage or 'deleted by the owner' in webpage:
-            raise ExtractorError('File not found', expected=True)
-
-        ol_id = self._search_regex(
-            '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
-            webpage, 'openload ID')
-
-        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 % 12
-
-            A = hashMap[index]
-            i ^= 213
-            i ^= A
-            video_url_chars.append(compat_chr(i))
-            H += 1
-
-        video_url = 'https://openload.co/stream/%s?mime=true'
-        video_url = video_url % (''.join(video_url_chars))
+            raise ExtractorError('File not found', expected=True, video_id=video_id)
+
+        phantom = PhantomJSwrapper(self, required_version='2.0')
+        webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers)
+
+        decoded_id = get_element_by_id('streamurl', webpage)
+
+        video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
@@ -127,15 +92,17 @@ class OpenloadIE(InfoExtractor):
             'description', webpage, 'title', fatal=True)
 
         entries = self._parse_html5_media_entries(url, webpage, video_id)
-        subtitles = entries[0]['subtitles'] if entries else None
+        entry = entries[0] if entries else {}
+        subtitles = entry.get('subtitles')
 
         info_dict = {
             'id': video_id,
             'title': title,
-            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
             # Seems all videos have extensions in their titles
             'ext': determine_ext(title, 'mp4'),
             'subtitles': subtitles,
+            'http_headers': headers,
         }
         return info_dict