parent
e4e4d540cf
commit
c62ba45101
@ -0,0 +1,20 @@
|
||||
import urllib.request
|
||||
import urllib.parse
|
||||
from lxml import etree
|
||||
import ssl
|
||||
|
||||
ssl._create_default_https_context = ssl._create_unverified_context
|
||||
|
||||
url='https://www.news.cn/'
|
||||
headers = {
|
||||
'User-Agent':' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36'
|
||||
}
|
||||
request = urllib.request.Request(url=url,headers=headers)
|
||||
response = urllib.request.urlopen(request)
|
||||
content = response.read().decode('utf-8')
|
||||
tree = etree.HTML(content)
|
||||
news_names=tree.xpath("//div[@class='depth-cont']//a/text()")
|
||||
news_names_list=news_names[:10]
|
||||
for news_name in news_names_list:
|
||||
with open('胡文浩.txt','a',encoding='utf-8') as f:
|
||||
f.write(news_name+'\n')
|
||||
Loading…
Reference in new issue