Support CCTV Plamforms

This commit is contained in:
2025-08-15 01:08:53 +08:00
parent ac98ac0057
commit 89909d2781
5 changed files with 18 additions and 18 deletions

View File

@@ -3,36 +3,32 @@ from core.models import Website
from core.utils import full_site_crawler
# jimmy.fang:20250815: 因 CCTV 的视频有做加密动作,无法下载,移除支持
class Command(BaseCommand):
help = "全站递归爬取 中央广播电视总台及其子网站、客户端、新媒体平台"
def add_arguments(self, parser):
parser.add_argument('--platform', type=str, default='all',
choices=['cctv', 'cctvnews', 'mobile', 'all'],
help='选择爬取平台: cctv(央视网), cctvnews(央视新闻), mobile(移动端), all(全部)')
help='选择爬取平台: cctv(央视网), cctvnews(央视新闻), all(全部)')
def handle(self, *args, **options):
platform = options['platform']
# 中央广播电视总台各平台配置
platforms = {
'cctv': {
'name': '央视网',
'base_url': 'https://www.cctv.com',
'start_url': 'https://www.cctv.com',
'article_selector': 'a'
},
# jimmy.fang:20250815: 因 CCTV 的视频有做加密动作,无法下载,移除支持
# 'cctv': {
# 'name': '央视网',
# 'base_url': 'https://www.cctv.com',
# 'start_url': 'https://www.cctv.com',
# 'article_selector': 'a'
# },
'cctvnews': {
'name': '央视新闻',
'base_url': 'https://news.cctv.com',
'start_url': 'https://news.cctv.com',
'article_selector': 'a'
},
'mobile': {
'name': '央视移动端',
'base_url': 'https://m.cctv.com',
'start_url': 'https://m.cctv.com',
'article_selector': 'a'
}
}