add extractor for skypixel.com

resolves https://github.com/rg3/youtube-dl/issues/13495

youtube_dl/extractor/common.py

@@ -809,6 +809,28 @@ class InfoExtractor(object):
         else:
             return res
 
+    def _simple_search_between(self, search_str, start_str, end_str):
+        """
+        Searches string for a starting substring followed by an ending substring
+        and returns the substring in between. If starting or ending substring are
+        not found returns None.
+        @search_str [str, unicode]
+        @start_str [str, unicode]
+        @end_str [str, unicode]
+        """
+        assert(type(search_str) in (str, unicode))
+        assert(type(start_str) in (str, unicode))
+        assert(type(end_str) in (str, unicode))
+        search_start = search_str.find(start_str)
+        if search_start == -1:
+            return None
+        between_a = search_start + len(start_str)
+        search_end = search_str[between_a:].find(end_str)
+        if search_end == -1:
+            return None
+        between_b = search_end + between_a
+        return search_str[between_a:between_b]
+
     def _get_netrc_login_info(self, netrc_machine=None):
         username = None
         password = None

youtube_dl/extractor/extractors.py

@@ -928,6 +928,7 @@ from .shared import (
 from .showroomlive import ShowRoomLiveIE
 from .sina import SinaIE
 from .sixplay import SixPlayIE
+from .skypixel import SkypixelIE
 from .skylinewebcams import SkylineWebcamsIE
 from .skynewsarabia import (
     SkyNewsArabiaIE,

youtube_dl/extractor/skypixel.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class SkypixelIE(InfoExtractor):
+    """InfoExtractor for Skypixel.com"""
+
+    _VALID_URL = r'https?://(?:www\.)?skypixel\.com/share/video/(?P<id>[^&#]+)'
+    _TESTS = [
+        {
+            'url': 'https://skypixel.com/share/video/check-out-my-latest-artwork-4f90b8ac-e7c3-4ed8-82c2-203addfd629e',
+            'info_dict': {
+                'id': 'check-out-my-latest-artwork-4f90b8ac-e7c3-4ed8-82c2-203addfd629e',
+                'ext': 'mp4',
+                'title': 'Check out my latest artwork!',
+                'uploader': 'Alby98',
+                'thumbnail': 'http://dn-djidl2.qbox.me/cloud/c89382b0b8dc75ea9f07354e098e0971/2.jpg',
+            },
+            'params': {
+                'noplaylist': True,
+                'skip_download': True,
+            }
+        },
+        {
+            'url': 'https://www.skypixel.com/share/video/undirfellsrett-i-vatnsdal-8-9-2017',
+            'info_dict': {
+                'id': 'undirfellsrett-i-vatnsdal-8-9-2017',
+                'ext': 'mp4',
+                'title': 'Undirfellsrétt í Vatnsdal 8/9/2017',
+                'uploader': 'Flokmundur',
+                'thumbnail': 'http://dn-djidl2.qbox.me/cloud/3c1a3aea1bdc042362a36ed482edb3ae/2.jpg',
+            },
+            'params': {
+                'noplaylist': True,
+                'skip_download': True,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        title = self._og_search_title(webpage).strip()
+        title = title.replace(' | SkyPixel.com', '')
+        uploader = self._simple_search_between(
+            webpage, u'<span itemprop="author">', u'</span>')
+        assert(uploader is not None)
+        djivideos_url = self._simple_search_between(
+            webpage, u'<iframe frameborder="0" scrolling="no" src="', u'">')
+        assert(djivideos_url is not None)
+        djivideos_webpage = self._download_webpage(
+            djivideos_url, 'djivideos.com[%s]' % (video_id, ))
+        video_definitions_json = self._simple_search_between(
+            djivideos_webpage, u'JSON.parse(\'', u'\');')
+        assert(video_definitions_json is not None)
+        video_definitions = self._parse_json(video_definitions_json, video_id)
+        video_url = video_definitions[-1]['src']
+        thumbnail = self._simple_search_between(
+            djivideos_webpage, u'poster: "', u'",')
+        if thumbnail is not None:
+            url_params_start = thumbnail.find('?sign=')
+            if url_params_start != -1:
+                thumbnail = thumbnail[:url_params_start]
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'uploader': uploader,
+            'thumbnail': thumbnail,
+        }