debian/control: Update list of extractors in long description.

[youtubedl] / youtube_dl / extractor / xfileshare.py

diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py
index de344bad25309c03b1d7378ceb6b3968c2d4c47a..b38c7a7b3cd5f87a33f814444fd70af3219afb93 100644 (file)
--- a/youtube_dl/extractor/xfileshare.py
+++ b/youtube_dl/extractor/xfileshare.py
@@ -6,31 +6,36 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     decode_packed_codes,
 from .common import InfoExtractor
 from ..utils import (
     decode_packed_codes,

+    determine_ext,

     ExtractorError,
     int_or_none,
     NO_DEFAULT,
     ExtractorError,
     int_or_none,
     NO_DEFAULT,

-    sanitized_Request,

     urlencode_postdata,
 )
 
 
 class XFileShareIE(InfoExtractor):
     _SITES = (
     urlencode_postdata,
 )
 
 
 class XFileShareIE(InfoExtractor):
     _SITES = (

-        ('daclips.in', 'DaClips'),
-        ('filehoot.com', 'FileHoot'),
-        ('gorillavid.in', 'GorillaVid'),
-        ('movpod.in', 'MovPod'),
-        ('powerwatch.pw', 'PowerWatch'),
-        ('rapidvideo.ws', 'Rapidvideo.ws'),
-        ('thevideobee.to', 'TheVideoBee'),
-        ('vidto.me', 'Vidto'),
-        ('streamin.to', 'Streamin.To'),
-        ('xvidstage.com', 'XVIDSTAGE'),
+        (r'daclips\.(?:in|com)', 'DaClips'),
+        (r'filehoot\.com', 'FileHoot'),
+        (r'gorillavid\.(?:in|com)', 'GorillaVid'),
+        (r'movpod\.in', 'MovPod'),
+        (r'powerwatch\.pw', 'PowerWatch'),
+        (r'rapidvideo\.ws', 'Rapidvideo.ws'),
+        (r'thevideobee\.to', 'TheVideoBee'),
+        (r'vidto\.(?:me|se)', 'Vidto'),
+        (r'streamin\.to', 'Streamin.To'),
+        (r'xvidstage\.com', 'XVIDSTAGE'),
+        (r'vidabc\.com', 'Vid ABC'),
+        (r'vidbom\.com', 'VidBom'),
+        (r'vidlo\.us', 'vidlo'),
+        (r'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'),
+        (r'fastvideo\.me', 'FastVideo.me'),

     )
 
     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
     _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
     )
 
     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
     _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'

-                  % '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
+                  % '|'.join(site for site in list(zip(*_SITES))[0]))

 
     _FILE_NOT_FOUND_REGEXES = (
         r'>(?:404 - )?File Not Found<',
 
     _FILE_NOT_FOUND_REGEXES = (
         r'>(?:404 - )?File Not Found<',


@@ -44,7 +49,7 @@ class XFileShareIE(InfoExtractor):
             'id': '06y9juieqpmi',
             'ext': 'mp4',
             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
             'id': '06y9juieqpmi',
             'ext': 'mp4',
             'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',

-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',

         },
     }, {
         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
         },
     }, {
         'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',


@@ -56,7 +61,7 @@ class XFileShareIE(InfoExtractor):
             'id': '3rso4kdn6f9m',
             'ext': 'mp4',
             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
             'id': '3rso4kdn6f9m',
             'ext': 'mp4',
             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',

-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',

         }
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         }
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',


@@ -67,7 +72,7 @@ class XFileShareIE(InfoExtractor):
             'id': '3ivfabn7573c',
             'ext': 'mp4',
             'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
             'id': '3ivfabn7573c',
             'ext': 'mp4',
             'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',

-            'thumbnail': 're:http://.*\.jpg',
+            'thumbnail': r're:http://.*\.jpg',

         },
         'skip': 'Video removed',
     }, {
         },
         'skip': 'Video removed',
     }, {


@@ -95,8 +100,36 @@ class XFileShareIE(InfoExtractor):
         # removed by administrator
         'url': 'http://xvidstage.com/amfy7atlkx25',
         'only_matching': True,
         # removed by administrator
         'url': 'http://xvidstage.com/amfy7atlkx25',
         'only_matching': True,

+    }, {
+        'url': 'http://vidabc.com/i8ybqscrphfv',
+        'info_dict': {
+            'id': 'i8ybqscrphfv',
+            'ext': 'mp4',
+            'title': 're:Beauty and the Beast 2017',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.rapidvideo.cool/b667kprndr8w',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://vidto.se/1tx1pf6t12cg.html',
+        'only_matching': True,

     }]
 
     }]
 

+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url')
+            for mobj in re.finditer(
+                r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1'
+                % '|'.join(site for site in list(zip(*XFileShareIE._SITES))[0]),
+                webpage)]
+

     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')


@@ -116,12 +149,12 @@ class XFileShareIE(InfoExtractor):
             if countdown:
                 self._sleep(countdown, video_id)
 
             if countdown:
                 self._sleep(countdown, video_id)
 

-            post = urlencode_postdata(fields)
-
-            req = sanitized_Request(url, post)
-            req.add_header('Content-type', 'application/x-www-form-urlencoded')
-
-            webpage = self._download_webpage(req, video_id, 'Downloading video page')
+            webpage = self._download_webpage(
+                url, video_id, 'Downloading video page',
+                data=urlencode_postdata(fields), headers={
+                    'Referer': url,
+                    'Content-type': 'application/x-www-form-urlencoded',
+                })

 
         title = (self._search_regex(
             (r'style="z-index: [0-9]+;">([^<]+)</span>',
 
         title = (self._search_regex(
             (r'style="z-index: [0-9]+;">([^<]+)</span>',


@@ -133,31 +166,45 @@ class XFileShareIE(InfoExtractor):
             webpage, 'title', default=None) or self._og_search_title(
             webpage, default=None) or video_id).strip()
 
             webpage, 'title', default=None) or self._og_search_title(
             webpage, default=None) or video_id).strip()
 

-        def extract_video_url(default=NO_DEFAULT):
-            return self._search_regex(
-                (r'file\s*:\s*(["\'])(?P<url>http.+?)\1,',
-                 r'file_link\s*=\s*(["\'])(?P<url>http.+?)\1',
-                 r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http.+?)\2\)',
-                 r'<embed[^>]+src=(["\'])(?P<url>http.+?)\1'),
-                webpage, 'file url', default=default, group='url')
-
-        video_url = extract_video_url(default=None)
-
-        if not video_url:
+        def extract_formats(default=NO_DEFAULT):
+            urls = []
+            for regex in (
+                    r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
+                    r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
+                    r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
+                    r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
+                for mobj in re.finditer(regex, webpage):
+                    video_url = mobj.group('url')
+                    if video_url not in urls:
+                        urls.append(video_url)
+            formats = []
+            for video_url in urls:
+                if determine_ext(video_url) == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        video_url, video_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id='hls',
+                        fatal=False))
+                else:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': 'sd',
+                    })
+            if not formats and default is not NO_DEFAULT:
+                return default
+            self._sort_formats(formats)
+            return formats
+
+        formats = extract_formats(default=None)
+
+        if not formats:

             webpage = decode_packed_codes(self._search_regex(
                 r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
                 webpage, 'packed code'))
             webpage = decode_packed_codes(self._search_regex(
                 r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
                 webpage, 'packed code'))

-            video_url = extract_video_url()
+            formats = extract_formats()

 
         thumbnail = self._search_regex(
             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 
 
         thumbnail = self._search_regex(
             r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
 

-        formats = [{
-            'format_id': 'sd',
-            'url': video_url,
-            'quality': 1,
-        }]
-

         return {
             'id': video_id,
             'title': title,
         return {
             'id': video_id,
             'title': title,