R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

add mp3 support for RJ

Browse Source
This commit is contained in:
Hormoz K 2018-08-04 10:32:24 -04:00
parent 042e6581cb
commit 6403be9611
3 changed files with 62 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docs/supportedsites.md
View File

@ -690,7 +690,8 @@
- **radiocanada**
- **RadioCanadaAudioVideo**
- **radiofrance**
- **RadioJavan**
- **RadioJavanMp3**
- **RadioJavanVideo**
- **Rai**
- **RaiPlay**
- **RaiPlayLive**

5
youtube_dl/extractor/extractors.py
View File

@ -886,7 +886,10 @@ from .radiocanada import (
RadioCanadaAudioVideoIE,
)
from .radiode import RadioDeIE
from .radiojavan import RadioJavanIE
from .radiojavan import (
RadioJavanVideoIE,
RadioJavanMp3IE,
)
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .rai import (

84
youtube_dl/extractor/radiojavan.py
View File

@ -10,44 +10,23 @@ from ..utils import (
)
class RadioJavanIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
_HOST_TRACKER_URL = 'https://www.radiojavan.com/videos/video_host'
_TEST = {
'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
'info_dict': {
'id': 'chaartaar-ashoobam',
'ext': 'mp4',
'title': 'Chaartaar - Ashoobam',
'thumbnail': r're:^https?://.*\.jpe?g$',
'upload_date': '20150215',
'view_count': int,
'like_count': int,
'dislike_count': int,
}
}
class RadioJavanBaseIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
media_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, media_id)
download_host = self._download_json(
self._HOST_TRACKER_URL,
video_id,
data=urlencode_postdata({'id': video_id}),
media_id,
data=urlencode_postdata({'id': media_id}),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': url,
}
)['host']
formats = [{
'url': '%s/%s' % (download_host, video_path),
'format_id': '%sp' % height,
'height': int(height),
} for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
formats = self.get_formats(webpage, download_host)
self._sort_formats(formats)
title = self._og_search_title(webpage)
@ -68,7 +47,7 @@ class RadioJavanIE(InfoExtractor):
webpage, 'dislike count', fatal=False))
return {
'id': video_id,
'id': media_id,
'title': title,
'thumbnail': thumbnail,
'upload_date': upload_date,
@ -77,3 +56,52 @@ class RadioJavanIE(InfoExtractor):
'dislike_count': dislike_count,
'formats': formats,
}
class RadioJavanVideoIE(RadioJavanBaseIE):
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
_HOST_TRACKER_URL = 'https://www.radiojavan.com/videos/video_host'
_TEST = {
'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
'info_dict': {
'id': 'chaartaar-ashoobam',
'ext': 'mp4',
'title': 'Chaartaar - Ashoobam',
'thumbnail': r're:^https?://.*\.jpe?g$',
'upload_date': '20150215',
'view_count': int,
'like_count': int,
'dislike_count': int,
}
}
def get_formats(self, webpage, download_host):
return [{
'url': '%s/%s' % (download_host, video_path),
'format_id': '%sp' % height,
'height': int(height),
} for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
class RadioJavanMp3IE(RadioJavanBaseIE):
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/mp3s/mp3/(?P<id>[^/?]+)/?'
_HOST_TRACKER_URL = 'https://www.radiojavan.com/mp3s/mp3_host'
_TEST = {
'url': 'https://www.radiojavan.com/mp3s/mp3/Mazyar-Fallahi-Baran-Fallahi-Begoo-Boro',
'md5': '9601a5a94ced3a2f772f8d18170a8920',
'info_dict': {
'id': 'Mazyar-Fallahi-Baran-Fallahi-Begoo-Boro',
'ext': 'mp3',
'title': 'Mazyar Fallahi & Baran Fallahi - Begoo Boro',
'thumbnail': r're:^https?://.*\.jpe?g$',
'upload_date': '20180729',
'view_count': int,
'like_count': int,
'dislike_count': int,
}
}
def get_formats(self, webpage, download_host):
mp3_path = re.findall(r"RJ\.currentMP3Url\s*=\s*'/?([^']+)'", webpage)[0]
return [{'url': '%s/media/%s.mp3' % (download_host, mp3_path)}]