pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-01-08 12:30:10 +09:00
Code Issues Projects Releases Wiki Activity

use _og_search_title for fallback playlist title ; use digitalconcerthall API for individual playlist item titles

Browse Source
This commit is contained in:
Robert Jacobson 2020-04-04 19:51:09 -04:00
parent cddf55300d
commit 32fdbd27fa
1 changed files with 14 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
youtube_dl/extractor/digitalconcerthall.py
View File

@ -4,10 +4,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_id,
)
class DigitalConcertHallIE(InfoExtractor):
@ -32,18 +28,26 @@ class DigitalConcertHallIE(InfoExtractor):
self.to_screen('[debug] %s' % args)
def _real_extract(self, url):
MAX_TITLE_LENGTH = 128
language, video_id = re.match(self._VALID_URL, url).groups()
if not language:
language = 'en'
self.debug_out("url: " + url + " video_id: " + video_id + " language: " + language)
webpage = self._download_webpage(url, video_id)
playlist_title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
playlist_title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title') \
or self._og_search_title(webpage)
self.debug_out("playlist_title: " + playlist_title)
# this returns JSON containing the urls of the playlist
# Note: you must be authenticated to get the stream info
playlist_dict = self._download_json(
'https://www.digitalconcerthall.com/json_services/get_stream_urls?id='
+ video_id + "&language=" + language, video_id).get('urls')
+ video_id + "&language=" + language, video_id, note='Downloading Stream JSON').get('urls')
# use the API to get other information about the concert
vid_info_dict = self._download_json(
'https://api.digitalconcerthall.com/v2/concert/'
+ video_id, video_id, headers={'Accept': 'application/json',
'Accept-Language': language}).get('_embedded')
entries = []
for key in playlist_dict:
@ -53,11 +57,10 @@ class DigitalConcertHallIE(InfoExtractor):
formats = self._extract_m3u8_formats(
m3u8_url, key, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
self.debug_out(formats)
# the div with id=key contains the video title
vid_info_div = clean_html(get_element_by_id(key, webpage))
self.debug_out("vid_info_div:\n" + vid_info_div)
title = re.sub(r'\s+', ' ', vid_info_div) \
or self._og_search_title(webpage)
title = [vid_info_dict.get(x)[0].get('title',"unknown title") for x in vid_info_dict
if vid_info_dict.get(x)[0].get('id') == key][0]
# avoid filenames that exceed filesystem limits
title = (title[:MAX_TITLE_LENGTH] + '..') if len(title) > MAX_TITLE_LENGTH else title
self.debug_out("title: " + title)
entries.append({
'id': key,