From 185a7e25e7c18b0dff17bdb9ae828616a5ac17d4 Mon Sep 17 00:00:00 2001 From: Mohammad Teimori Pabandi Date: Fri, 3 Apr 2015 20:55:39 +0430 Subject: [PATCH] [RadioJavan] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/radiojavan.py | 71 ++++++++++++++++++++++++++++++ 2 files changed, 72 insertions(+) create mode 100644 youtube_dl/extractor/radiojavan.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3011b784d2..df4a7419a2 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -391,6 +391,7 @@ 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 0000000000..de90f92706 --- /dev/null +++ b/youtube_dl/extractor/radiojavan.py @@ -0,0 +1,71 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import( + parse_duration, + str_to_int +) + +class RadioJavanIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P[^/]+)/?' + _TEST = { + 'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam', + 'md5': 'e85208ffa3ca8b83534fca9fe19af95b', + 'info_dict': { + 'id': 'chaartaar-ashoobam', + 'ext': 'mp4', + 'title': 'Chaartaar - Ashoobam', + 'description': 'Chaartaar - Ashoobam', + 'thumbnail': 're:^https?://.*\.jpe?g$', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + urls = list() + prefix = 'https://media.rdjavan.com/media/music_video/' + + video_url_480 = self._search_regex( + r'RJ\.video480p = \'([^\']+)\'', webpage, '480 video url', fatal= False) + video_url_720 = self._search_regex( + r'RJ\.video720p = \'([^\']+)\'', webpage, '720 video url', fatal= False) + video_url_1080 = self._search_regex( + r'RJ\.video1080p = \'([^\']+)\'', webpage, '1080 video url', fatal= False) + + if video_url_480: + urls.append({'url': prefix + video_url_480, 'format': '480p'}) + if video_url_720: + urls.append({'url': prefix + video_url_720, 'format': '720p'}) + if video_url_1080: + urls.append({'url': prefix + video_url_1080, 'format': '1080p'}) + + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + formats = [{ + 'url': url['url'], + 'format': url['format'] + } for url in urls] + + likes = self._search_regex( + r'([\d,]+)\s*likes', webpage, 'Likes Count', fatal=False ) + likes = likes.replace(',', '') + dislikes = self._search_regex( + r'([\d,]+)\s*dislikes', webpage, 'Dislikes Count', fatal=False ) + dislikes = dislikes.replace(',', '') + + plays = self._search_regex( + r'views_publish[">\s]*]+class="views">Plays: ([\d,]+)', webpage, 'Play Count', fatal=False ) + plays = plays.replace(',', '') + + return { + 'formats': formats, + 'id': display_id, + 'title': title, + 'description': title, # no description provided in RadioJavan + 'thumbnail': thumbnail, + 'like_count': str_to_int(likes), + 'dislike_count': str_to_int(dislikes), + 'viewCount': str_to_int(plays) + } \ No newline at end of file