[xfileshare] Add support for vidabc.com (closes #12589)

[youtube-dl] / youtube_dl / extractor / xfileshare.py

diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py
index 995aada0d1565ccc76f2fa2c7654e3f53f834d91..6856fb3bf2fd720754f9facd04d67bcd6a27f651 100644 (file)
--- a/youtube_dl/extractor/xfileshare.py
+++ b/youtube_dl/extractor/xfileshare.py
@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     decode_packed_codes,
+    determine_ext,
     ExtractorError,
     int_or_none,
     NO_DEFAULT,
@@ -26,6 +27,7 @@ class XFileShareIE(InfoExtractor):
         ('vidto.me', 'Vidto'),
         ('streamin.to', 'Streamin.To'),
         ('xvidstage.com', 'XVIDSTAGE'),
+        ('vidabc.com', 'Vid ABC'),
     )
 
     IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
@@ -44,7 +46,7 @@ class XFileShareIE(InfoExtractor):
             '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',
@@ -56,7 +58,7 @@ 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',
@@ -67,7 +69,7 @@ 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',
     }, {
@@ -95,6 +97,16 @@ class XFileShareIE(InfoExtractor):
         # 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):
@@ -124,38 +136,54 @@ 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()
-
-        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:
+             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'))
-            video_url = extract_video_url()
+            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,