[internazionale] Add extractor
authorLeonardo Taccari <iamleot@gmail.com>
Wed, 13 Dec 2017 11:24:07 +0000 (12:24 +0100)
committerSergey M․ <dstftw@gmail.com>
Wed, 27 Dec 2017 16:27:43 +0000 (23:27 +0700)
youtube_dl/extractor/extractors.py
youtube_dl/extractor/internazionale.py [new file with mode: 0644]

index 04125d9f22f722bd9d76b996c93ee24b80234f96..e7b93a699f0bcd60b70774d855681b09766ef638 100644 (file)
@@ -466,6 +466,7 @@ from .indavideo import (
 )
 from .infoq import InfoQIE
 from .instagram import InstagramIE, InstagramUserIE
+from .internazionale import InternazionaleIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
 from .iqiyi import IqiyiIE
diff --git a/youtube_dl/extractor/internazionale.py b/youtube_dl/extractor/internazionale.py
new file mode 100644 (file)
index 0000000..2ebf05d
--- /dev/null
@@ -0,0 +1,46 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class InternazionaleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?P<id>.*)'
+    _TESTS = [{
+        'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood',
+        'md5': '11b54a3d3333e455c00684e50a65c58e',
+        'info_dict': {
+            'id': '265968',
+            'ext': 'mp4',
+            'description': 'md5:efb7e5bbfb1a54ae2ed5a4a015f0e665',
+            'title': 'Richard Linklater racconta una scena di Boyhood',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        data_job_id = self._html_search_regex(r'data-job-id="([^"]+)"', webpage, 'data-job-id')
+        data_video_path = self._html_search_regex(r'data-video-path="([^"]+)"', webpage, 'data-video-path')
+
+        formats = []
+
+        formats.extend(self._extract_m3u8_formats(
+            'https://video.internazionale.it/%s/%s.m3u8' % (data_video_path, data_job_id),
+            video_id))
+
+        formats.extend(self._extract_mpd_formats(
+            'https://video.internazionale.it/%s/%s.mpd' % (data_video_path, data_job_id),
+            video_id))
+
+        self._sort_formats(formats)
+
+        return {
+            'id': data_job_id,
+            'title': self._og_search_title(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': self._og_search_description(webpage),
+            'formats': formats,
+        }