Merge pull request #14225 from Tithen-Firion/openload-phantomjs-method

Openload phantomjs method

youtube_dl/extractor/common.py

@@ -2449,10 +2449,12 @@ class InfoExtractor(object):
                 self._downloader.report_warning(msg)
         return res
 
-    def _set_cookie(self, domain, name, value, expire_time=None):
+    def _set_cookie(self, domain, name, value, expire_time=None, port=None,
+                    path='/', secure=False, discard=False, rest={}, **kwargs):
         cookie = compat_cookiejar.Cookie(
-            0, name, value, None, None, domain, None,
-            None, '/', True, False, expire_time, '', None, None, None)
+            0, name, value, port, not port is None, domain, True,
+            domain.startswith('.'), path, True, secure, expire_time,
+            discard, None, None, rest)
         self._downloader.cookiejar.set_cookie(cookie)
 
     def _get_cookies(self, url):

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(
@@ -66,47 +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)
+            raise ExtractorError('File not found', expected=True, video_id=video_id)
 
-        ol_id = self._search_regex(
-            '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
-            webpage, 'openload ID')
+        phantom = PhantomJSwrapper(self, required_version='2.0')
+        webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers)
 
-        decoded = ''
-        a = ol_id[0:24]
-        b = []
-        for i in range(0, len(a), 8):
-            b.append(int(a[i:i + 8] or '0', 16))
-        ol_id = ol_id[24:]
-        j = 0
-        k = 0
-        while j < len(ol_id):
-            c = 128
-            d = 0
-            e = 0
-            f = 0
-            _more = True
-            while _more:
-                if j + 1 >= len(ol_id):
-                    c = 143
-                f = int(ol_id[j:j + 2] or '0', 16)
-                j += 2
-                d += (f & 127) << e
-                e += 7
-                _more = f >= c
-            g = d ^ b[k % 3]
-            for i in range(4):
-                char_dec = (g >> 8 * i) & (c + 127)
-                char = compat_chr(char_dec)
-                if char != '#':
-                    decoded += char
-            k += 1
+        decoded_id = get_element_by_id('streamurl', webpage)
 
-        video_url = 'https://openload.co/stream/%s?mime=true'
-        video_url = video_url % decoded
+        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,
@@ -114,15 +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