lunax/haruhi-dl
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

[onnetwork] refactor

Browse source
This commit is contained in:
Lauren Liberda 2021-03-10 17:51:52 +01:00
parent 9e535b8762
commit 199edacd48
2 changed files with 35 additions and 40 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
haruhi_dl/extractor/generic.py
View file

@ -2212,12 +2212,12 @@ class GenericIE(InfoExtractor):
# OnNetwork.tv embed
'url': 'https://wiadomosci.gazeta.pl/wiadomosci/7,114883,26377890,panstwo-polskie-nie-uznaje-takich-rodzin-jak-nasza-i-krzywdzi.html',
'info_dict': {
'id': '337382',
'title': 'Rodzina+ odc. 1. Karolina i Ania',
'ext': 'm3u8',
'age_limit': 16,
'upload_date': '20200929',
'id': '7,114883,26377890,panstwo-polskie-nie-uznaje-takich-rodzin-jak-nasza-i-krzywdzi',
'title': '"Państwo polskie nie uznaje takich rodzin jak nasza i krzywdzi w ten sposób dzieci" [RODZINA+]',
'uploader': 'wiadomosci.gazeta.pl',
},
# 1x onnetwork:script, which resolves to onnetwork:frame
'playlist_count': 1,
},
{
# Embetty video embeds (youtube, vimeo, facebook)

65
haruhi_dl/extractor/onnetwork.py
View file

@ -3,10 +3,10 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
js_to_json,
)
import re
import datetime
class OnNetworkLoaderIE(InfoExtractor):
@ -45,51 +45,46 @@ class OnNetworkLoaderIE(InfoExtractor):
class OnNetworkFrameIE(InfoExtractor):
IE_NAME = 'onnetwork:frame'
_VALID_URL = r'https?://video\.onnetwork\.tv/frame84\.php\?(?:[^&]+&)*?mid=(?P<mid>[^&]+)&(?:[^&]+&)*?id=(?P<vid>[^&]+)'
_VALID_URL = r'https?://video\.onnetwork\.tv/frame\d+\.php\?(?:[^&]+&)*?mid=(?P<mid>[^&]+)&(?:[^&]+&)*?id=(?P<vid>[^&]+)'
_TESTS = [{
'url': 'https://video.onnetwork.tv/frame84.php?mid=MCwxNng5LDAsMCwxNzU1LDM3MjksMSwwLDEsMzYsNSwwLDIsMCw0LDEsMCwxLDEsMiwwLDAsMSwwLDAsMCwwLC0xOy0xOzIwOzIwLDAsNTAsMA==&preview=0&iid=0&e=1&widget=524&id=ffEXS991c5f8f4dbb502b540687287098d2d8',
'only_matching': True,
}]
_BASE_OBJECT_RE = r'''var onplayer\s*=\s*new tUIPlayer\(\s*{\s*videos\s*:\s*\[\s*{.*?'''
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
vid = mobj.group('vid')
webpage = self._download_webpage(url, vid, 'Downloading video frame')
video_id = self._search_regex(
self._BASE_OBJECT_RE + r'id\s*:\s*(\d+)',
webpage, 'video id')
m3u_url = self._search_regex(
self._BASE_OBJECT_RE + r'(?:urls\s*:\[{[^}]+}\],)?url\s*:"([^"]+)"',
webpage, 'm3u url')
title = self._search_regex(
self._BASE_OBJECT_RE + r"(?<!p)title\s*:\s*'([^']+)'",
webpage, 'title')
thumbnail = self._search_regex(
self._BASE_OBJECT_RE + r"""(?<![a-z])poster\s*:\s*'([^']+)'""",
webpage, 'thumbnail', fatal=False)
duration = self._search_regex(
self._BASE_OBJECT_RE + r'duration\s*:\s*(\d+)',
webpage, 'duration', fatal=False)
age_limit = self._search_regex(
self._BASE_OBJECT_RE + r'ageallow\s*:\s*(\d+)',
webpage, 'age limit', fatal=False)
upload_date_unix = self._search_regex(
self._BASE_OBJECT_RE + r'adddate\s*:\s*(\d+)',
webpage, 'upload date', fatal=False)
if upload_date_unix:
upload_date = datetime.datetime.fromtimestamp(int(upload_date_unix)).strftime('%Y%m%d')
data = self._search_regex(
r'(?s)var onplayer\s*=\s*new tUIPlayer\(\s*({\s*videos\s*:\s*\[\s*{.*?})\s*,\s*OnPlayerUI',
webpage, 'video data')
data = js_to_json(data)
data = re.sub(
r'\((?P<value>\d+(?:\.\d+)?|(["\']).+?\2)(?:\s*\|\|\s*.+?)?\)',
lambda x: x.group('value'), data)
data = re.sub(r'"\s*\+\s*"', '', data)
data = self._parse_json(data, vid)
formats = self._extract_m3u8_formats(m3u_url, video_id)
entries = []
for video in data['videos']:
video_id = str(video['id'])
formats = self._extract_m3u8_formats(video['url'], video_id)
self._sort_formats(formats)
entries.append({
'id': video_id,
'title': video['title'],
'formats': formats,
'thumbnail': video.get('poster'),
'duration': int_or_none(video.get('duration')),
'age_limit': int_or_none(video.get('ageallow')),
'timestamp': int_or_none(video.get('adddate')),
})
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'duration': int_or_none(duration),
'age_limit': int_or_none(age_limit),
'upload_date': upload_date,
'_type': 'playlist',
'entries': entries,
'id': vid,
}