Files
RSSHub-python/rsshub/spiders/xinhuanet/utils.py
2023-07-01 22:56:58 +00:00

15 lines
380 B
Python

from rsshub.utils import DEFAULT_HEADERS, fetch
def parse_html(post):
item = {}
item['title'] = post.xpath('text()').extract_first()
item['link'] = post.xpath('@href').extract_first()
print(item['link'])
item['description'] = (
fetch(item['link'], headers=DEFAULT_HEADERS)
.xpath('//div[@id=\'detail\']')
.get()
)
return item