Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 16:44:32 +01:00
Code Issues Releases Wiki Activity

Fix issue #20264 Lrt.lt site redesign

Browse Source 
As part of the fix the following changes were made to video attributes:
* duration - removed
* view_count - removed
* like_count - removed
* release_date - added
This commit is contained in:
Linas Jakucionis 2019-03-28 22:16:47 +13:00
parent c4c888697e
commit bc9abd4db7
1 changed files with 27 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
youtube_dl/extractor/lrt.py
View File

@ -6,8 +6,6 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
int_or_none,
parse_duration,
remove_end, remove_end,
) )
@ -17,70 +15,67 @@ class LRTIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)'
_TESTS = [{ _TESTS = [{
# m3u8 download # m3u8 download
'url': 'http://www.lrt.lt/mediateka/irasas/54391/', 'url': 'https://www.lrt.lt/mediateka/irasas/54391/septynios-kauno-dienos',
'md5': 'fe44cf7e4ab3198055f2c598fc175cb0', 'md5': '50c84b875e930784daa66fa8c2617664',
'info_dict': { 'info_dict': {
'id': '54391', 'id': '54391',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Septynios Kauno dienos', 'title': 'Septynios Kauno dienos',
'description': 'md5:24d84534c7dc76581e59f5689462411a', 'description': 'md5:24d84534c7dc76581e59f5689462411a',
'duration': 1783,
'view_count': int,
'like_count': int,
}, },
}, { }, {
# direct mp3 download # after the redesign - everything is mp4 file (some of the shows used to be mp3)
'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/', 'url': 'https://www.lrt.lt/mediateka/irasas/1013074524/kita-tema-2016-09-05-15-05',
'md5': '389da8ca3cad0f51d12bed0c844f6a0a', 'md5': 'e286cd475ad2839ab90c2ec0be57930b',
'info_dict': { 'info_dict': {
'id': '1013074524', 'id': '1013074524',
'ext': 'mp3', 'ext': 'mp4',
'title': 'Kita tema 2016-09-05 15:05', 'title': 'Kita tema 2016-09-05 15:05',
'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5', 'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5',
'duration': 3008,
'view_count': int,
'like_count': int,
}, },
}] }]
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(url, video_id) webpage = self._download_webpage(url, video_id)
title = remove_end(self._og_search_title(webpage), ' - LRT') title = remove_end(self._og_search_title(webpage), ' - LRT')
file_url1 = ""
urlinfo = ""
formats = [] formats = []
for _, file_url in re.findall( for _, file_url in re.findall(
r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage): r'(main_url) = "(.*)";', webpage):
ext = determine_ext(file_url) urlinfo = self._download_json("https://www.lrt.lt/servisai/stream_url/vod/media_info/?url=" + file_url, video_id)
file_url1 = urlinfo.get("playlist_item").get("file")
release_date_string_temp = urlinfo.get("date")
release_date = release_date_string_temp[0:4] + release_date_string_temp[5:7] + release_date_string_temp[8:10]
ext = determine_ext(file_url1)
if ext not in ('m3u8', 'mp3'): if ext not in ('m3u8', 'mp3'):
continue continue
# mp3 served as m3u8 produces stuttered media file # mp3 served as m3u8 produces stuttered media file
if ext == 'm3u8' and '.mp3' in file_url: if ext == 'm3u8' and '.mp3' in file_url1:
continue continue
if ext == 'm3u8': if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native', file_url1, video_id, 'mp4', entry_protocol='m3u8_native',
fatal=False)) fatal=False))
elif ext == 'mp3': elif ext == 'mp3':
formats.append({ formats.append({
'url': file_url, 'url': file_url1,
'vcodec': 'none', 'vcodec': 'none',
}) })
self._sort_formats(formats) self._sort_formats(formats)
thumbnail = self._og_search_thumbnail(webpage) try:
description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage)
duration = parse_duration(self._search_regex( except:
r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1', thumbnail = 0
webpage, 'duration', default=None, group='duration'))
view_count = int_or_none(self._html_search_regex( description = urlinfo.get("content")
r'<div[^>]+class=(["\']).*?record-desc-seen.*?\1[^>]*>(?P<count>.+?)</div>',
webpage, 'view count', fatal=False, group='count'))
like_count = int_or_none(self._search_regex(
r'<span[^>]+id=(["\'])flikesCount.*?\1>(?P<count>\d+)<',
webpage, 'like count', fatal=False, group='count'))
return { return {
'id': video_id, 'id': video_id,
@ -88,7 +83,5 @@ class LRTIE(InfoExtractor):
'formats': formats, 'formats': formats,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'description': description, 'description': description,
'duration': duration, 'release_date': release_date
'view_count': view_count,
'like_count': like_count,
} }