diff options
author | Sergey M․ <dstftw@gmail.com> | 2015-04-04 16:47:24 +0600 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2015-04-04 16:47:24 +0600 |
commit | f1ce35af1a6626e4153e60fe6f8a82f0f7e0d1a3 (patch) | |
tree | b5607bb6aa49d35f44684a8fa1fe401672e929dd /youtube_dl/extractor | |
parent | ff556f5c09ec8700bb012a58a5e39505b887b774 (diff) | |
parent | 6e617ed0b6b5bb932f928f63c2bda36f5317468d (diff) |
Merge branch 'mtp1376-radiojavan'
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/radiojavan.py | 66 |
2 files changed, 67 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index aae4aae4c..d7e8138be 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -396,6 +396,7 @@ from .pyvideo import PyvideoIE from .quickvid import QuickVidIE from .r7 import R7IE from .radiode import RadioDeIE +from .radiojavan import RadioJavanIE from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE from .rai import RaiIE 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, + } |