Merge branch 'mtp1376-radiojavan'

1 files changed, 66 insertions, 0 deletions

diff --git a/youtube_dl/extractor/radiojavan.py b/youtube_dl/extractor/radiojavan.py
new file mode 100644
index 000000000..73ab78d6d
--- /dev/null
+++ b/youtube_dl/extractor/radiojavan.py
@@ -0,0 +1,66 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import(
+    unified_strdate,
+    str_to_int,
+)
+
+
+class RadioJavanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
+    _TEST = {
+        'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
+        'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
+        'info_dict': {
+            'id': 'chaartaar-ashoobam',
+            'ext': 'mp4',
+            'title': 'Chaartaar - Ashoobam',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
+            'upload_date': '20150215',
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = [{
+            'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
+            'format_id': '%sp' % height,
+            'height': height,
+        } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
+
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        upload_date = unified_strdate(self._search_regex(
+            r'class="date_added">Date added: ([^<]+)<',
+            webpage, 'upload date', fatal=False))
+
+        view_count = str_to_int(self._search_regex(
+            r'class="views">Plays: ([\d,]+)',
+            webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._search_regex(
+            r'class="rating">([\d,]+) likes',
+            webpage, 'like count', fatal=False))
+        dislike_count = str_to_int(self._search_regex(
+            r'class="rating">([\d,]+) dislikes',
+            webpage, 'dislike count', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'formats': formats,
+        }