debian/README.source: Change 'markup'.

[youtubedl] / youtube_dl / extractor / openload.py

diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index b50d6c77b4e2fad46bf3d5ada798f1cb8f255a29..679eaf6c312d0d4de0a3e11bee7076f6ec365039 100644 (file)
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -42,9 +42,9 @@ def cookie_to_dict(cookie):
     if cookie.discard is not None:
         cookie_dict['discard'] = cookie.discard
     try:
     if cookie.discard is not None:
         cookie_dict['discard'] = cookie.discard
     try:

-        if (cookie.has_nonstandard_attr('httpOnly') or
-                cookie.has_nonstandard_attr('httponly') or
-                cookie.has_nonstandard_attr('HttpOnly')):
+        if (cookie.has_nonstandard_attr('httpOnly')
+                or cookie.has_nonstandard_attr('httponly')
+                or cookie.has_nonstandard_attr('HttpOnly')):

             cookie_dict['httponly'] = True
     except TypeError:
         pass
             cookie_dict['httponly'] = True
     except TypeError:
         pass


@@ -112,6 +112,8 @@ class PhantomJSwrapper(object):
         return get_exe_version('phantomjs', version_re=r'([0-9.]+)')
 
     def __init__(self, extractor, required_version=None, timeout=10000):
         return get_exe_version('phantomjs', version_re=r'([0-9.]+)')
 
     def __init__(self, extractor, required_version=None, timeout=10000):

+        self._TMP_FILES = {}
+

         self.exe = check_executable('phantomjs', ['-v'])
         if not self.exe:
             raise ExtractorError('PhantomJS executable not found in PATH, '
         self.exe = check_executable('phantomjs', ['-v'])
         if not self.exe:
             raise ExtractorError('PhantomJS executable not found in PATH, '


@@ -130,7 +132,6 @@ class PhantomJSwrapper(object):
         self.options = {
             'timeout': timeout,
         }
         self.options = {
             'timeout': timeout,
         }

-        self._TMP_FILES = {}

         for name in self._TMP_FILE_NAMES:
             tmp = tempfile.NamedTemporaryFile(delete=False)
             tmp.close()
         for name in self._TMP_FILE_NAMES:
             tmp = tempfile.NamedTemporaryFile(delete=False)
             tmp.close()


@@ -140,7 +141,7 @@ class PhantomJSwrapper(object):
         for name in self._TMP_FILE_NAMES:
             try:
                 os.remove(self._TMP_FILES[name].name)
         for name in self._TMP_FILE_NAMES:
             try:
                 os.remove(self._TMP_FILES[name].name)

-            except:
+            except (IOError, OSError, KeyError):

                 pass
 
     def _save_cookies(self, url):
                 pass
 
     def _save_cookies(self, url):


@@ -242,8 +243,26 @@ class PhantomJSwrapper(object):
 
 
 class OpenloadIE(InfoExtractor):
 
 
 class OpenloadIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
-
+    _DOMAINS = r'''
+                    (?:
+                        openload\.(?:co|io|link|pw)|
+                        oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website|vip)|
+                        oladblock\.(?:services|xyz|me)|openloed\.co
+                    )
+                '''
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?P<host>
+                            (?:www\.)?
+                            %s
+                        )/
+                        (?:f|embed)/
+                        (?P<id>[a-zA-Z0-9-_]+)
+                    ''' % _DOMAINS
+    _EMBED_WORD = 'embed'
+    _STREAM_WORD = 'f'
+    _REDIR_WORD = 'stream'
+    _URL_IDS = ('streamurl', 'streamuri', 'streamurj')

     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
         'md5': 'bf1c059b004ebc7a256f89408e65c36e',
     _TESTS = [{
         'url': 'https://openload.co/f/kUEfGclsU9o',
         'md5': 'bf1c059b004ebc7a256f89408e65c36e',


@@ -283,55 +302,194 @@ class OpenloadIE(InfoExtractor):
         # for title and ext
         'url': 'https://openload.co/embed/Sxz5sADo82g/',
         'only_matching': True,
         # for title and ext
         'url': 'https://openload.co/embed/Sxz5sADo82g/',
         'only_matching': True,

+    }, {
+        # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available
+        # via https://openload.co/f/e-Ixz9ZR5L0/
+        'url': 'https://openload.co/f/e-Ixz9ZR5L0/',
+        'only_matching': True,

     }, {
         'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
         'only_matching': True,
     }, {
         'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
         'only_matching': True,

+    }, {
+        'url': 'http://www.openload.link/f/KnG-kKZdcfY',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.stream/f/KnG-kKZdcfY',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.xyz/f/WwRBpzW8Wtk',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.win/f/kUEfGclsU9o',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.download/f/kUEfGclsU9o',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.cloud/f/4ZDnBXRWiB8',
+        'only_matching': True,
+    }, {
+        # Its title has not got its extension but url has it
+        'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.cc/embed/5NEAbI2BDSk',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.icu/f/-_i4y_F_Hs8',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.fun/f/gb6G1H4sHXY',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.club/f/Nr1L-aZ2dbQ',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.info/f/5NEAbI2BDSk',
+        'only_matching': True,
+    }, {
+        'url': 'https://openload.pw/f/WyKgK8s94N0',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.pw/f/WyKgK8s94N0',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.live/f/-Z58UZ-GR4M',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.space/f/IY4eZSst3u8/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.services/embed/bs1NWj1dCag/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.press/embed/drTBl1aOTvk/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.website/embed/drTBl1aOTvk/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.life/embed/oOzZjNPw9Dc/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.biz/f/bEk3Gp8ARr4/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.best/embed/kkz9JgVZeWc/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oladblock.xyz/f/b8NWEgkqNLI/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oladblock.me/f/b8NWEgkqNLI/',
+        'only_matching': True,
+    }, {
+        'url': 'https://openloed.co/f/b8NWEgkqNLI/',
+        'only_matching': True,
+    }, {
+        'url': 'https://oload.vip/f/kUEfGclsU9o',
+        '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):
+    @classmethod
+    def _extract_urls(cls, webpage):

         return re.findall(
         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)
-        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, video_id=video_id)
+            r'(?x)<iframe[^>]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)'
+            % (cls._DOMAINS, cls._EMBED_WORD), webpage)

 
 

+    def _extract_decrypted_page(self, page_url, webpage, video_id):

         phantom = PhantomJSwrapper(self, required_version='2.0')
         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)
+        webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id)
+        return webpage

 
 

-        video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        video_id = mobj.group('id')
+
+        url_pattern = 'https://%s/%%s/%s/' % (host, video_id)
+
+        for path in (self._EMBED_WORD, self._STREAM_WORD):
+            page_url = url_pattern % path
+            last = path == self._STREAM_WORD
+            webpage = self._download_webpage(
+                page_url, video_id, 'Downloading %s webpage' % path,
+                fatal=last)
+            if not webpage:
+                continue
+            if 'File not found' in webpage or 'deleted by the owner' in webpage:
+                if not last:
+                    continue
+                raise ExtractorError('File not found', expected=True, video_id=video_id)
+            break
+
+        webpage = self._extract_decrypted_page(page_url, webpage, video_id)
+        for element_id in self._URL_IDS:
+            decoded_id = get_element_by_id(element_id, webpage)
+            if decoded_id:
+                break
+        if not decoded_id:
+            decoded_id = self._search_regex(
+                (r'>\s*([\w-]+~\d{10,}~\d+\.\d+\.0\.0~[\w-]+)\s*<',
+                 r'>\s*([\w~-]+~\d+\.\d+\.\d+\.\d+~[\w~-]+)',
+                 r'>\s*([\w-]+~\d{10,}~(?:[a-f\d]+:){2}:~[\w-]+)\s*<',
+                 r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)\s*<',
+                 r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage,
+                'stream URL')
+        video_url = 'https://%s/%s/%s?mime=true' % (host, self._REDIR_WORD, decoded_id)

 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
             'title', default=None) or self._html_search_meta(
             'description', webpage, 'title', fatal=True)
 
 
         title = self._og_search_title(webpage, default=None) or self._search_regex(
             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
             'title', default=None) or self._html_search_meta(
             'description', webpage, 'title', fatal=True)
 

-        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        entries = self._parse_html5_media_entries(page_url, webpage, video_id)

         entry = entries[0] if entries else {}
         subtitles = entry.get('subtitles')
 
         entry = entries[0] if entries else {}
         subtitles = entry.get('subtitles')
 

-        info_dict = {
+        return {

             'id': video_id,
             'title': title,
             'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
             'url': video_url,
             'id': video_id,
             'title': title,
             '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'),
+            'ext': determine_ext(title, None) or determine_ext(url, 'mp4'),

             'subtitles': subtitles,
             'subtitles': subtitles,

-            'http_headers': headers,

         }
         }

-        return info_dict
+
+
+class VerystreamIE(OpenloadIE):
+    IE_NAME = 'verystream'
+
+    _DOMAINS = r'(?:verystream\.com|woof\.tube)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?P<host>
+                            (?:www\.)?
+                            %s
+                        )/
+                        (?:stream|e)/
+                        (?P<id>[a-zA-Z0-9-_]+)
+                    ''' % _DOMAINS
+    _EMBED_WORD = 'e'
+    _STREAM_WORD = 'stream'
+    _REDIR_WORD = 'gettoken'
+    _URL_IDS = ('videolink', )
+    _TESTS = [{
+        'url': 'https://verystream.com/stream/c1GWQ9ngBBx/',
+        'md5': 'd3e8c5628ccb9970b65fd65269886795',
+        'info_dict': {
+            'id': 'c1GWQ9ngBBx',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny.mp4',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+    }, {
+        'url': 'https://verystream.com/e/c1GWQ9ngBBx/',
+        'only_matching': True,
+    }]
+
+    def _extract_decrypted_page(self, page_url, webpage, video_id):
+        return webpage  # for Verystream, the webpage is already decrypted