aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2014-11-25 22:24:33 +0600
committerSergey M․ <dstftw@gmail.com>2014-11-25 22:24:33 +0600
commitb9ed3af34368e110e6ab2262ce908d2e8572f025 (patch)
tree5d6fe7a8a0a6a4de3cda1eff3257caa8fe26b09d /youtube_dl
parent63c9b2c1d916ec3e3d2ab5e5247ac8a372c7957e (diff)
[tass] Add extractor (Closes #4296)
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/tass.py62
2 files changed, 63 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 3e2133f5c..5c096542b 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -373,6 +373,7 @@ from .syfy import SyfyIE
from .sztvhu import SztvHuIE
from .tagesschau import TagesschauIE
from .tapely import TapelyIE
+from .tass import TassIE
from .teachertube import (
TeacherTubeIE,
TeacherTubeUserIE,
diff --git a/youtube_dl/extractor/tass.py b/youtube_dl/extractor/tass.py
new file mode 100644
index 000000000..c4ef70778
--- /dev/null
+++ b/youtube_dl/extractor/tass.py
@@ -0,0 +1,62 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ js_to_json,
+ qualities,
+)
+
+
+class TassIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)'
+ _TESTS = [
+ {
+ 'url': 'http://tass.ru/obschestvo/1586870',
+ 'md5': '3b4cdd011bc59174596b6145cda474a4',
+ 'info_dict': {
+ 'id': '1586870',
+ 'ext': 'mp4',
+ 'title': 'Посетителям московского зоопарка показали красную панду',
+ 'description': 'Приехавшую из Дублина Зейну можно увидеть в павильоне "Кошки тропиков"',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ },
+ {
+ 'url': 'http://itar-tass.com/obschestvo/1600009',
+ 'only_matching': True,
+ },
+ ]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ sources = json.loads(js_to_json(self._search_regex(
+ r'(?s)sources\s*:\s*(\[.+?\])', webpage, 'sources')))
+
+ quality = qualities(['sd', 'hd'])
+
+ formats = []
+ for source in sources:
+ video_url = source.get('file')
+ if not video_url or not video_url.startswith('http') or not video_url.endswith('.mp4'):
+ continue
+ label = source.get('label')
+ formats.append({
+ 'url': video_url,
+ 'format_id': label,
+ 'quality': quality(label),
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': self._og_search_title(webpage),
+ 'description': self._og_search_description(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'formats': formats,
+ }