Merge 07ae9e8805 into 956b8c5855

youtube_dl/extractor/darkibox.py

@@ -0,0 +1,120 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    decode_packed_codes,
+    determine_ext,
+    ExtractorError,
+    urlencode_postdata,
+)
+
+
+class DarkiboxIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?darkibox\.com/(?:embed-|d/)?(?P<id>[a-z0-9]+)(?:\.html)?'
+    IE_NAME = 'darkibox'
+    _TESTS = [{
+        'url': 'https://darkibox.com/embed-vku4mg7gc7wp.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://darkibox.com/vku4mg7gc7wp',
+        'only_matching': True,
+    }, {
+        'url': 'https://darkibox.com/d/vku4mg7gc7wp',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        embed_url = 'https://darkibox.com/embed-%s.html' % video_id
+        webpage = self._download_webpage(embed_url, video_id)
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)</title>', webpage, 'title', default=None)
+        if title:
+            title = re.sub(r'\s*-\s*Darkibox\s*$', '', title, flags=re.IGNORECASE).strip()
+        if not title:
+            title = video_id
+
+        # POST to /dl endpoint to get the player page
+        webpage = self._download_webpage(
+            'https://darkibox.com/dl', video_id,
+            note='Downloading player page',
+            data=urlencode_postdata({
+                'op': 'embed',
+                'file_code': video_id,
+                'auto': '1',
+            }),
+            headers={
+                'Referer': embed_url,
+                'Content-type': 'application/x-www-form-urlencoded',
+                'Origin': 'https://darkibox.com',
+            })
+
+        # Unpack eval(function(p,a,c,k,e,d){...}) if present
+        packed = self._search_regex(
+            r'(?s)(eval\(function\(p,a,c,k,e,d\)\{.+?\)\))',
+            webpage, 'packed code', default=None)
+        if packed:
+            webpage = decode_packed_codes(packed)
+
+        # Extract video URL from PlayerJS file:"URL" or sources
+        # Try file:"url" (PlayerJS format)
+        video_url = self._search_regex(
+            r'file\s*:\s*"([^"]+)"', webpage, 'video url', default=None)
+
+        if not video_url:
+            # Try [label]url format (multi-quality)
+            video_url = self._search_regex(
+                r'file\s*:\s*"(\[[^"]+\])"', webpage, 'video url list', default=None)
+
+        if not video_url:
+            # Try src: or source
+            video_url = self._search_regex(
+                r'(?:src|source)\s*[:=]\s*["\']([^"\']+\.(?:m3u8|mp4)[^"\']*)',
+                webpage, 'video url', default=None)
+
+        if not video_url:
+            raise ExtractorError('Unable to extract video URL', expected=True)
+
+        # Handle [label]url multi-quality format
+        # e.g. [720p]https://...,[480p]https://...
+        if video_url.startswith('['):
+            formats = []
+            for m in re.finditer(r'\[([^\]]+)\]([^,\s"]+)', video_url):
+                label, fmt_url = m.groups()
+                height = self._search_regex(
+                    r'(\d+)', label, 'height', default=None)
+                formats.append({
+                    'url': fmt_url,
+                    'format_id': label,
+                    'height': int(height) if height else None,
+                })
+            if not formats:
+                raise ExtractorError('Unable to parse multi-quality URLs', expected=True)
+        elif determine_ext(video_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(
+                video_url, video_id, 'mp4',
+                entry_protocol='m3u8_native', m3u8_id='hls',
+                fatal=False)
+        else:
+            formats = [{
+                'url': video_url,
+                'format_id': 'sd',
+            }]
+
+        self._sort_formats(formats)
+
+        thumbnail = self._search_regex(
+            r'image\s*:\s*"([^"]+)"', webpage, 'thumbnail', default=None)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'http_headers': {'Referer': embed_url},
+        }

youtube_dl/extractor/extractors.py

@@ -281,6 +281,7 @@ from .curiositystream import (
     CuriosityStreamCollectionIE,
 )
 from .cwtv import CWTVIE
+from .darkibox import DarkiboxIE
 from .dailymail import DailyMailIE
 from .dailymotion import (
     DailymotionIE,