You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

28 lines
1.2 KiB

import requests
import re
header = {"User-Agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Mobile Safari/537.36 Edg/122.0.0.0"}
urls=['https://www.jxxdxy.edu.cn/news-list-xiaoyuanyaowen-{}.html'.format(number) for number in range(1,21)]
all_url=[]
for url in urls:
#print(url)
all_url.append(url)
response = requests.get(url, headers=header,stream=True)
source=response.text
#print(source)
my_article1 = '<li>.*?<a href="(.*?)">(.*?)</a>.*?<span>(.*?)</span>.*?</li>'
regex1 = re.findall(my_article1, source, re.S)
#print(regex1)
my_article2=' <li>.*?<a href="(.*?)" .*>.*?<span class="fl"><.*?>(.*?产教融合.*?).*?</span>.*?<span class="fr timee">(.*?)</span>.*?</li>'
regex2 = re.findall(my_article2, source, re.S)
print(regex2)
my_article3 = '<li>.*?<a href=".*?">(.*?)</a>.*?<span>(03-.*?)</span>.*?</li>'
regex3 = re.findall(my_article3, source, re.S)
#print(regex3)
#print(len(regex3))
response1=requests.get(all_url[0])
source1=response1.text
#print(response1.status_code)
#print(response1.encoding)
#print(response1.text)