[Picarto] Add new extractor for recorded Picarto VODs

youtube_dl/extractor/extractors.py

@@ -799,6 +799,7 @@ from .periscope import (
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .picarto import PicartoVodIE 
 from .piksel import PikselIE
 from .pinkbike import PinkbikeIE
 from .pladform import PladformIE

youtube_dl/extractor/picarto.py

@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class PicartoVodIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?picarto\.tv/videopopout/(?P<id>[a-zA-Z_\-.0-9]+).flv'
+    _TEST = {
+        'url': 'https://picarto.tv/videopopout/Carrot_2018.01.11.07.55.12.flv',
+        'md5': '1ecd32f358fee23d8b3e6954880f78d4',
+        'info_dict': {
+            'id': 'Carrot_2018.01.11.07.55.12',
+            'ext': 'm3u8',
+            'title': 'Carrot_2018.01.11.07.55.12',
+            'thumbnail': r're:^https?://.*\.jpg$'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        vod_regex = "<script[^<]*>[^<]*riot.mount\(([^<]+)\)[^<]*<\/"
+        vod_script = self._html_search_regex(vod_regex, webpage, "vod_script")
+        vod_url = self._search_regex('vod: \\"([^\\"]*)\\"', vod_script, "vod_url")
+        vod_thumb = self._search_regex('vodThumb: \\"([^\\"]*)\\"', vod_script, "vod_thumb")
+
+        title = video_id
+        
+        return {
+            'id': video_id,
+            'title': title,
+            'description': "",
+            'uploader': "",
+            'url' : vod_url,
+            'thumbnail' : vod_thumb
+        }