Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-01-08 14:17:54 +01:00
Code Issues Releases Wiki Activity

[narando] add separate [narando:player] extractor

Browse Source
This commit is contained in:
ealgase 2018-11-21 15:20:41 -05:00
parent 200ad7687a
commit f8a4a38880
2 changed files with 35 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/extractors.py
View File

@ -672,7 +672,10 @@ from .myvi import (
MyviEmbedIE, MyviEmbedIE,
) )
from .myvidster import MyVidsterIE from .myvidster import MyVidsterIE
from .narando import NarandoIE from .narando import (
NarandoIE,
NarandoPlayerIE,
)
from .nationalgeographic import ( from .nationalgeographic import (
NationalGeographicVideoIE, NationalGeographicVideoIE,
NationalGeographicIE, NationalGeographicIE,

66
youtube_dl/extractor/narando.py
View File

@ -4,6 +4,33 @@ from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
class NarandoPlayerIE(InfoExtractor):
IE_NAME = "narando:player"
_VALID_URL = r'https://narando.com/widget\?r=(?P<id>\w+)'
_TEST = {
'url': 'https://narando.com/widget?r=b2t4t789kxgy9g7ms4rwjvvw',
'md5': 'd20f671f0395bab8f8285d1f6e8f965e',
'info_dict': {
'id': 'b2t4t789kxgy9g7ms4rwjvvw',
'ext': 'mp3',
'title': 'An ihrem Selbstlob erkennt man sie',
'url': 'https://static.narando.com/sounds/10492/original.mp3',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage('https://narando.com/widget?r=' + video_id, video_id)
title = self._html_search_regex(r'<title>narando \| (.+?)</title>', webpage, 'title')
download_url = self._html_search_regex(r'.<div class="stream_url hide">\s*([^?]*)', webpage, 'download_url')
return {
'id': video_id,
'title': title,
'url': download_url,
}
class NarandoIE(InfoExtractor): class NarandoIE(InfoExtractor):
IE_NAME = "narando" IE_NAME = "narando"
_VALID_URL = r'https?://(?:www\.)?narando\.com/articles/(?P<id>([a-zA-Z]|-)+)' _VALID_URL = r'https?://(?:www\.)?narando\.com/articles/(?P<id>([a-zA-Z]|-)+)'
@ -22,48 +49,17 @@ class NarandoIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage('https://narando.com/articles/' + video_id, video_id) webpage = self._download_webpage('https://narando.com/articles/' + video_id, video_id)
title = self._html_search_regex(r'<h1 class="visible-xs h3">(.+?)</h1>', webpage, 'title') title = self._html_search_regex(r'<h1 class="visible-xs h3">(.+?)</h1>', webpage, 'title')
player_id = self._html_search_regex(r'[\n\r].*https:\/\/narando.com\/r\/\s*([^"]*)', webpage, 'player_id') player_id = self._html_search_regex(r'[\n\r].*https:\/\/narando.com\/r\/\s*([^"]*)', webpage, 'player_id')
player_page = self._download_webpage('https://narando.com/widget?r=' + player_id, player_id) player_url = 'https://narando.com/widget?r=' + player_id
download_url = self._html_search_regex(r'.<div class="stream_url hide">\s*([^?]*)', player_page, 'url')
# download_url = NarandoPlayerIE()._real_extract('https://narando.com/widget?r=' + player_id)['url']
description = self._html_search_regex(r'<meta content="(.+?)" property="og:description" />', webpage, 'description') description = self._html_search_regex(r'<meta content="(.+?)" property="og:description" />', webpage, 'description')
return { return {
'display_id': video_id, 'display_id': video_id,
'id': player_id, 'id': player_id,
'title': title, 'title': title,
'url': download_url, 'url': player_url,
'description': description, 'description': description,
'_type': 'url',
} }
"""to be implemented later
class NarandoPlayerIE(InfoExtractor):
IE_NAME = "narando:player"
_VALID_URL = r'https://narando.com/widget\?r=(?P<id>\w+)'
_TEST = {
'url': 'https://narando.com/widget?r=b2t4t789kxgy9g7ms4rwjvvw',
'md5': 'd20f671f0395bab8f8285d1f6e8f965e',
'info_dict': {
'id': 'b2t4t789kxgy9g7ms4rwjvvw',
'ext': 'mp3',
'title': 'An ihrem Selbstlob erkennt man sie',
'url': 'https://static.narando.com/sounds/10492/original.mp3',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage('https://narando.com/widget?r=' + video_id, video_id)
title = self._html_search_regex(r'<title>narando \| (.+?)</title>', webpage, 'title')
download_url = self._html_search_regex(r'.<div class="stream_url hide">\s*([^?]*)', webpage, 'download_url')
return {
'id': video_id,
'title': title,
'url': download_url,
}
"""