X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxfileshare.py;h=1b5cd122ac9f5c90ff8b846c998bceff36ba350a;hb=89beedd31f8a00a811787b651a506001833da0e1;hp=ee4d04c205a1f6f0ea2ba2e047399ca04877fa38;hpb=436214baf70c1a50fbaf1fbfca4b48f33695590c;p=youtube-dl

diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py
index ee4d04c20..1b5cd122a 100644
--- a/youtube_dl/extractor/xfileshare.py
+++ b/youtube_dl/extractor/xfileshare.py
@@ -5,8 +5,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    decode_packed_codes,
+    determine_ext,
     ExtractorError,
     int_or_none,
+    NO_DEFAULT,
     sanitized_Request,
     urlencode_postdata,
 )
@@ -23,22 +26,29 @@ class XFileShareIE(InfoExtractor):
         ('thevideobee.to', 'TheVideoBee'),
         ('vidto.me', 'Vidto'),
         ('streamin.to', 'Streamin.To'),
+        ('xvidstage.com', 'XVIDSTAGE'),
+        ('vidabc.com', 'Vid ABC'),
+        ('vidbom.com', 'VidBom'),
+        ('vidlo.us', 'vidlo'),
     )
 
     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]))
 
-    _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
+    _FILE_NOT_FOUND_REGEXES = (
+        r'>(?:404 - )?File Not Found<',
+        r'>The file was removed by administrator<',
+    )
 
     _TESTS = [{
         'url': 'http://gorillavid.in/06y9juieqpmi',
         'md5': '5ae4a3580620380619678ee4875893ba',
         'info_dict': {
             'id': '06y9juieqpmi',
-            'ext': 'flv',
+            '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',
@@ -50,7 +60,7 @@ class XFileShareIE(InfoExtractor):
             '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',
@@ -61,7 +71,7 @@ class XFileShareIE(InfoExtractor):
             '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',
     }, {
@@ -78,6 +88,27 @@ class XFileShareIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Big Buck Bunny trailer',
         },
+    }, {
+        'url': 'http://xvidstage.com/e0qcnl03co6z',
+        'info_dict': {
+            'id': 'e0qcnl03co6z',
+            'ext': 'mp4',
+            'title': 'Chucky Prank 2015.mp4',
+        },
+    }, {
+        # 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,
+        },
     }]
 
     def _real_extract(self, url):
@@ -87,7 +118,7 @@ class XFileShareIE(InfoExtractor):
         url = 'http://%s/%s' % (mobj.group('host'), video_id)
         webpage = self._download_webpage(url, video_id)
 
-        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+        if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         fields = self._hidden_inputs(webpage)
@@ -107,25 +138,54 @@ class XFileShareIE(InfoExtractor):
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
         title = (self._search_regex(
-            [r'style="z-index: [0-9]+;">([^<]+)</span>',
+            (r'style="z-index: [0-9]+;">([^<]+)</span>',
              r'<td nowrap>([^<]+)</td>',
              r'h4-fine[^>]*>([^<]+)<',
              r'>Watch (.+) ',
-             r'<h2 class="video-page-head">([^<]+)</h2>'],
-            webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
-        video_url = self._search_regex(
-            [r'file\s*:\s*["\'](http[^"\']+)["\'],',
-             r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
-            webpage, 'file url')
+             r'<h2 class="video-page-head">([^<]+)</h2>',
+             r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'),  # streamin.to
+            webpage, 'title', default=None) or self._og_search_title(
+            webpage, default=None) or video_id).strip()
+
+        def extract_formats(default=NO_DEFAULT):
+            urls = []
+            for regex in (
+                    r'file\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'))
+            formats = extract_formats()
+
         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,