import requests
from lxml import etree
import re

header = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36 Edg/122.0.0.0"}
r = requests.get('https://www.jxxdxy.edu.cn/news-list-xiaoyuanyaowen.html', headers=header)
#print(r.text)
text = r.content.decode('utf-8')

dom = etree.HTML(text)
block = dom.xpath('//div[@class="pages_con"]/span/select/option')
n = 0
url_lists = ['https://www.jxxdxy.edu.cn/news-list-xiaoyuanyaowen.html']
for i in block:
    if (n < 20):
        if (n == 0):
            n += 1
            continue
        else:
            url_lists.append(i.get('value'))
            n = n + 1
    else:
        break

encoding_lists = []
status_lists = []
allCjrh = []
allMarch = []
all_20 = []
all = set()

for i in url_lists:
    res = requests.get(i, headers=header)
    encoding_lists.append(res.encoding)
    status_lists.append(res.status_code)

    if i == url_lists[0]:
        print(res.text)

    res_text = res.content.decode('utf-8')

    # 发布时间、标题及链接
    pattern = r'<a.*?title="(.*?)".*?href="(.*?)".*?<span.*?>(.*?)</span>'
    matches = re.findall(pattern, res_text)
    for match in matches:
        all_20.append([match[2], match[0], match[1]])

    # 获取标题内容包含“产教融合”的文章标题、发布时间及链接
    pattern_cjrh = r'<a.*?title="(.*?产教融合.*?)".*?href="(.*?)".*?<span.*?>(.*?)</span>'
    matches_cjrh = re.findall(pattern_cjrh, res_text)
    for match in matches_cjrh:
        allCjrh.append([match[0], match[1], match[2]])

    # 获取发布时间为 2024 年 3 月份的文章数量及所有文章标题
    pattern_march = r'<a.*?<span.*?>(2024-03.*?)</span>'
    matches_march = re.findall(pattern_march, res_text)
    for match in matches_march:
        for ii in all_20:
            if ii[0] == match:
                all.add(ii[1])

print(encoding_lists)
print(status_lists)
print(allCjrh)
print(allMarch)
print(all_20)
print(all)