Update upstream source from tag 'upstream/2020.03.24'

[youtubedl] / youtube_dl / extractor / shared.py

diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py
index badba2ac61ca5f46db325e5064f6e75425c60cbb..02295d1a4cacf570ee903c06161b072f35a6da77 100644 (file)
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -1,19 +1,59 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-import base64
-

 from .common import InfoExtractor
 from .common import InfoExtractor

+from ..compat import (
+    compat_b64decode,
+    compat_urllib_parse_unquote_plus,
+)

 from ..utils import (
 from ..utils import (

+    determine_ext,

     ExtractorError,
     ExtractorError,

-    compat_urllib_request,
-    compat_urllib_parse,

     int_or_none,
     int_or_none,

+    js_to_json,
+    KNOWN_EXTENSIONS,
+    parse_filesize,
+    rot47,
+    url_or_none,
+    urlencode_postdata,

 )
 
 
 )
 
 

-class SharedIE(InfoExtractor):
-    _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})'
+class SharedBaseIE(InfoExtractor):
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+
+        if self._FILE_NOT_FOUND in webpage:
+            raise ExtractorError(
+                'Video %s does not exist' % video_id, expected=True)
+
+        video_url = self._extract_video_url(webpage, video_id, url)
+
+        title = self._extract_title(webpage)
+        filesize = int_or_none(self._extract_filesize(webpage))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'filesize': filesize,
+            'title': title,
+        }
+
+    def _extract_title(self, webpage):
+        return compat_b64decode(self._html_search_meta(
+            'full:title', webpage, 'title')).decode('utf-8')
+
+    def _extract_filesize(self, webpage):
+        return self._html_search_meta(
+            'full:size', webpage, 'file size', fatal=False)
+
+
+class SharedIE(SharedBaseIE):
+    IE_DESC = 'shared.sx'
+    _VALID_URL = r'https?://shared\.sx/(?P<id>[\da-z]{10})'
+    _FILE_NOT_FOUND = '>File does not exist<'

 
     _TEST = {
         'url': 'http://shared.sx/0060718775',
 
     _TEST = {
         'url': 'http://shared.sx/0060718775',


@@ -22,36 +62,77 @@ class SharedIE(InfoExtractor):
             'id': '0060718775',
             'ext': 'mp4',
             'title': 'Bmp4',
             'id': '0060718775',
             'ext': 'mp4',
             'title': 'Bmp4',

+            'filesize': 1720110,

         },
     }
 
         },
     }
 

-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        page = self._download_webpage(url, video_id)
+    def _extract_video_url(self, webpage, video_id, url):
+        download_form = self._hidden_inputs(webpage)

 
 

-        if re.search(r'>File does not exist<', page) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+        video_page = self._download_webpage(
+            url, video_id, 'Downloading video page',
+            data=urlencode_postdata(download_form),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Referer': url,
+            })

 
 

-        download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page))
+        video_url = self._html_search_regex(
+            r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            video_page, 'video URL', group='url')

 
 

-        request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form))
-        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        return video_url

 
 

-        video_page = self._download_webpage(request, video_id, 'Downloading video page')

 
 

-        video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL')
-        title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8')
-        filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False))
-        thumbnail = self._html_search_regex(
-            r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None)
+class VivoIE(SharedBaseIE):
+    IE_DESC = 'vivo.sx'
+    _VALID_URL = r'https?://vivo\.sx/(?P<id>[\da-z]{10})'
+    _FILE_NOT_FOUND = '>The file you have requested does not exists or has been removed'

 
 

-        return {
-            'id': video_id,
-            'url': video_url,
+    _TEST = {
+        'url': 'http://vivo.sx/d7ddda0e78',
+        'md5': '15b3af41be0b4fe01f4df075c2678b2c',
+        'info_dict': {
+            'id': 'd7ddda0e78',

             'ext': 'mp4',
             'ext': 'mp4',

-            'filesize': filesize,
-            'title': title,
-            'thumbnail': thumbnail,
-        }
\ No newline at end of file
+            'title': 'Chicken',
+            'filesize': 515659,
+        },
+    }
+
+    def _extract_title(self, webpage):
+        title = self._html_search_regex(
+            r'data-name\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1', webpage,
+            'title', default=None, group='title')
+        if title:
+            ext = determine_ext(title)
+            if ext.lower() in KNOWN_EXTENSIONS:
+                title = title.rpartition('.' + ext)[0]
+            return title
+        return self._og_search_title(webpage)
+
+    def _extract_filesize(self, webpage):
+        return parse_filesize(self._search_regex(
+            r'data-type=["\']video["\'][^>]*>Watch.*?<strong>\s*\((.+?)\)',
+            webpage, 'filesize', fatal=False))
+
+    def _extract_video_url(self, webpage, video_id, url):
+        def decode_url_old(encoded_url):
+            return compat_b64decode(encoded_url).decode('utf-8')
+
+        stream_url = self._search_regex(
+            r'data-stream\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'stream url', default=None, group='url')
+        if stream_url:
+            stream_url = url_or_none(decode_url_old(stream_url))
+        if stream_url:
+            return stream_url
+
+        def decode_url(encoded_url):
+            return rot47(compat_urllib_parse_unquote_plus(encoded_url))
+
+        return decode_url(self._parse_json(
+            self._search_regex(
+                r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage,
+                'stream'),
+            video_id, transform_source=js_to_json)['source'])