videotarget extractor

haruhi_dl/extractor/extractors.py

@@ -1474,6 +1474,7 @@ from .videomore import (
     VideomoreSeasonIE,
 )
 from .videopress import VideoPressIE
+from .videotarget import VideoTargetIE
 from .vidio import VidioIE
 from .vidlii import VidLiiIE
 from .vidme import (

haruhi_dl/extractor/pulsembed.py

@@ -24,6 +24,7 @@ from .libsyn import LibsynIE
 from .xnews import XLinkIE
 from .tvp import TVPEmbedIE
 from .acast import ACastPlayerIE
+from .videotarget import VideoTargetIE
 
 
 class PulseVideoIE(InfoExtractor):
@@ -190,6 +191,13 @@ class PulsEmbedIE(InfoExtractor):
             'upload_date': '20210208',
             'timestamp': 1612764000,
         },
+    }, {
+        'url': 'pulsembed:P_Q2gen3E',
+        'info_dict': {
+            'id': '16028',
+            'ext': 'mp4',
+            'title': 'Słabe szanse na taki wzrost gospodarczy o jakim mówi rząd',
+        },
     }]
 
     @staticmethod
@@ -202,6 +210,10 @@ class PulsEmbedIE(InfoExtractor):
             return 'TVP'
         if '//html5-player.libsyn.com/' in ext_url:
             return 'Libsyn'
+        if '//player.acast.com/' in ext_url:
+            return 'ACastPlayer'
+        if '//videotarget.pl/' in ext_url:
+            return 'VideoTarget'
         return None
 
     @staticmethod
@@ -271,6 +283,7 @@ class PulsEmbedIE(InfoExtractor):
                 XLinkIE,
                 TVPEmbedIE,
                 ACastPlayerIE,
+                VideoTargetIE,
                 PulseVideoIE,
             ):
                 embie_urls = embie._extract_urls(webpage, url=referer)

haruhi_dl/extractor/videotarget.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+
+import base64
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    js_to_json,
+)
+
+
+class VideoTargetIE(InfoExtractor):
+    _VALID_URL = r'https?://videotarget\.pl/player/v1/content/(?P<id>[a-zA-Z\d_-]+={0,3})'
+
+    _TESTS = [{
+        'url': 'https://videotarget.pl/player/v1/content/eyJzaXRlIjoxMDMzLCJwbGFjZW1lbnQiOjEwNzksInRlbXBsYXRlIjoyLCJjb250ZXh0IjoxNjA2NiwidHlwZSI6ImNvbnRlbnQifQ==?type=content',
+        'info_dict': {
+            'id': '16066',
+            'ext': 'mp4',
+            'title': 'Inflacja straszy rynki finansowe, niepokoją zwłaszcza rosnące ceny namu mieszkań',
+        },
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage, **kw):
+        return [mobj.group('url')
+                for mobj in re.finditer(
+                    r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>%s(?:\?[^#]+)?(?:\#.+?)?)\1' % VideoTargetIE._VALID_URL,
+                    webpage)
+                ] + ['https://videotarget.pl/player/v1/content/' + mobj.group('vtid')
+                     for mobj in re.finditer(
+                         r'<div\b[^>]+?data-vt=(["\'])(?P<vtid>[a-zA-Z\d_-]+={0,3})\1',
+                         webpage)]
+
+    def _real_extract(self, url):
+        b64_json_ident = self._match_id(url)
+        ident = self._parse_json(
+            base64.urlsafe_b64decode(b64_json_ident), b64_json_ident)
+        video_id = str(ident['context'])
+
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<title>(.+?) - videotarget</title>', webpage, 'video title')
+
+        formats = []
+        for qual in re.finditer(r'(?s)videoQualities\.push\(({.+?})\);', webpage):
+            qual = self._parse_json(qual.group(1), video_id, js_to_json)
+            formats.append({
+                'height': int_or_none(qual['label'][:-1]),
+                'url': qual['src'].replace('{ext}', 'mp4'),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+        }