Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2025-01-07 13:47:54 +01:00
Code Issues Releases Wiki Activity

[narando] improve coding methods to match standards, add support for more URL formats

Browse Source
This commit is contained in:
ealgase 2019-01-20 19:00:43 -05:00
parent fc9ea7bd13
commit 83809b6ee1
2 changed files with 30 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
youtube_dl/extractor/extractors.py
View File

@ -674,7 +674,7 @@ from .myvi import (
from .myvidster import MyVidsterIE
from .narando import (
NarandoIE,
NarandoPlayerIE,
NarandoArticleIE,
)
from .nationalgeographic import (
NationalGeographicVideoIE,

47
youtube_dl/extractor/narando.py
View File

@ -4,9 +4,9 @@ from __future__ import unicode_literals
from .common import InfoExtractor
class NarandoPlayerIE(InfoExtractor):
IE_NAME = "narando:player"
_VALID_URL = r'https://narando\.com/widget\?r=(?P<id>\w+)'
class NarandoIE(InfoExtractor):
IE_NAME = 'narando'
_VALID_URL = r'https?://narando\.com/widget\?.*?r=(?P<id>\w+)&?'
_TEST = {
'url': 'https://narando.com/widget?r=b2t4t789kxgy9g7ms4rwjvvw',
'md5': 'd20f671f0395bab8f8285d1f6e8f965e',
@ -21,7 +21,7 @@ class NarandoPlayerIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<span class="clip-title">(.+?)</span>', webpage, 'title')
download_url = self._html_search_regex(r'.<div class="stream_url hide">\s*([^?]*)', webpage, 'download_url')
download_url = self._html_search_regex(r'<div class="stream_url hide">(.+)</div>', webpage, 'download_url')
return {
'id': video_id,
'title': title,
@ -30,29 +30,40 @@ class NarandoPlayerIE(InfoExtractor):
}
class NarandoIE(InfoExtractor):
IE_NAME = "narando"
_VALID_URL = r'https?://(?:www\.)?narando\.com/articles/(?P<id>.+)'
_TEST = {
'url': 'https://narando.com/articles/an-ihrem-selbstlob-erkennt-man-sie',
'md5': 'd20f671f0395bab8f8285d1f6e8f965e',
'info_dict': {
'id': 'b2t4t789kxgy9g7ms4rwjvvw',
'ext': 'mp3',
'title': 'An ihrem Selbstlob erkennt man sie',
class NarandoArticleIE(InfoExtractor):
IE_NAME = "narando:article"
_VALID_URL = r'https?://(?:www\.)?narando\.com/(articles|r)/(?P<id>.+)'
_TESTS = [
{
'url': 'https://narando.com/articles/an-ihrem-selbstlob-erkennt-man-sie',
'md5': 'd20f671f0395bab8f8285d1f6e8f965e',
'info_dict': {
'id': 'b2t4t789kxgy9g7ms4rwjvvw',
'ext': 'mp3',
'title': 'An ihrem Selbstlob erkennt man sie',
}
},
{
'url': 'https://narando.com/r/b2t4t789kxgy9g7ms4rwjvvw', #alternate URL format
'md5': 'd20f671f0395bab8f8285d1f6e8f965e',
'info_dict': {
'id': 'b2t4t789kxgy9g7ms4rwjvvw',
'ext': 'mp3',
'title': 'An ihrem Selbstlob erkennt man sie',
}
}
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1 class="visible-xs h3">(.+?)</h1>', webpage, 'title')
player_id = self._html_search_regex(r'\s*https://narando.com/r/([^"]*)', webpage, 'player_id')
player_url = 'https://narando.com/widget?r=' + player_id
player_id = self._html_search_regex(r'https://narando.com/r/(.+?)\"', webpage, 'player_id')
url_result = 'https://narando.com/widget?r=' + player_id
return {
'id': player_id,
'title': title,
'url': player_url,
'url': url_result,
'_type': 'url',
}