pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-01-10 13:30:09 +09:00
Code Issues Projects Releases Wiki Activity

get titles of playlist items and use debug instead of print

Browse Source
This commit is contained in:
Robert Jacobson 2020-03-21 21:39:44 -04:00
parent 831695a576
commit 2a11f19466
1 changed files with 22 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
youtube_dl/extractor/digitalconcerthall.py
View File

@ -4,6 +4,13 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
get_element_by_id,
get_element_by_attribute,
get_element_by_class,
)
class DigitalConcertHallIE(InfoExtractor): class DigitalConcertHallIE(InfoExtractor):
@ -18,23 +25,23 @@ class DigitalConcertHallIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Video title goes here', 'title': 'Video title goes here',
'thumbnail': r're:^https?://.*/images/core/Phil.*\.jpg$', 'thumbnail': r're:^https?://.*/images/core/Phil.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
} }
},] },]
def debug_out(self, args):
if not self._downloader.params.get('verbose', False):
return
self.to_screen('[debug] %s' % args)
def _real_extract(self, url): def _real_extract(self, url):
#video_id = self._match_id(url)
language, video_id = re.match(self._VALID_URL, url).groups() language, video_id = re.match(self._VALID_URL, url).groups()
if not language: if not language:
language = 'en' language = 'en'
print("url: ", url, " video_id: ", video_id, " language: ", language, "\n") self.debug_out("url: " + url + " video_id: " + video_id + " language: " + language)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title') title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
print("title: ", title, "\n") self.to_screen("title: " + title)
# this returns JSON, which contains the urls of the playlist # this returns JSON, which contains the urls of the playlist
#video_data = self._download_webpage( #video_data = self._download_webpage(
@ -44,11 +51,15 @@ class DigitalConcertHallIE(InfoExtractor):
entries = [] entries = []
for key in playlist_dict: for key in playlist_dict:
print("key: ", key, "\n") self.debug_out("key: " + key)
m3u8_url = playlist_dict[key][0]['url'] m3u8_url = playlist_dict[key][0]['url']
print("key url: ", m3u8_url, "\n") self.debug_out("key url: " + m3u8_url)
formats = self._extract_m3u8_formats(m3u8_url, key, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) formats = self._extract_m3u8_formats(m3u8_url, key, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
print("formats:\n", formats) self.debug_out(formats)
vid_info_div = clean_html(get_element_by_id(key, webpage))
self.debug_out("vid_info_div:\n" + vid_info_div)
title = re.sub('\s+', ' ', vid_info_div)
self.to_screen("title: " + title )
entries.append({ entries.append({
'id': key, 'id': key,
'title': title, 'title': title,