d0zingcat/RSSHub-python
1
0
Fork 0
mirror of https://github.com/d0zingcat/RSSHub-python.git synced 2026-05-20 15:09:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix xpath error in xinhuanet world

Browse Source
This commit is contained in:
Zhihai Liao
2023-07-01 22:23:25 +00:00
parent fec81fea05
commit b9b2fe90df
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
rsshub/spiders/xinhuanet/utils.py
View File

@@ -1,3 +1,4 @@
from time import sleep
from rsshub.utils import DEFAULT_HEADERS, fetch from rsshub.utils import DEFAULT_HEADERS, fetch
@@ -5,10 +6,11 @@ def parse_html(post):
item = {} item = {}
item['title'] = post.xpath('text()').extract_first() item['title'] = post.xpath('text()').extract_first()
item['link'] = post.xpath('@href').extract_first() item['link'] = post.xpath('@href').extract_first()
print(item['link']) html = fetch(item['link'], headers=DEFAULT_HEADERS)
item['description'] = ( item['description'] = (
fetch(item['link'], headers=DEFAULT_HEADERS) html
.xpath('//div[@id=\'detail\']') .xpath('//div[@id="detail"]')
.get() .get()
) )
return item sleep(1)
return item