import requests
from bs4 import BeautifulSoup
from lxml import etree

# 第一题:解析全部招聘会的详细信息的访问地址
# 目标网页URL
url = 'https://www.ncrczpw.com/index.php?m=jobfair&c=index&a=index'

head = {
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0"}
# 发送HTTP请求
response = requests.get(url, headers=head)
response.encoding = 'utf-8'
mySoup = BeautifulSoup(response.text, 'lxml')
result = mySoup.select('div.list div.td2 div.tit a, div.webList div.td2 div.tit a')  # 直接选择 a 标签
# 收录每个招聘会的详细信息的访问地址
recruits = []
for a_tag in result:
    href = a_tag.get('href')  # 从每个 a 标签中获取 href 属性
    if href:  # 确保 href 存在
        print(href)
        recruits.append(href)

print(len(recruits))  # 获取列表长度
# 第二题 :请求每个招聘会的详细信息页面，并解析出举办时间。。。
recruits_show = []  # 现场
for i in range(len(recruits)):
    if 'show' in recruits[i]:
        recruits_show.append(recruits[i])
recruits_last = []  # 网络
for i in range(len(recruits)):
    if 'com' in recruits[i]:
        recruits_last.append(recruits[i])
for url in recruits_show:
    res = requests.get(url, headers=head)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'lxml')
    result = soup.select('div.show_left div.txt,div.show_head div.tit a,div.show_right div.txt,div.nc_lf a strong')
    for i in result:
        print(i.get_text(strip=True),end=',')
    print(end='\n\n')
for url in recruits_last:
    res = requests.get(url, headers=head)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'lxml')
    result = soup.select('div.titleBox h1,div.dw,li a.companyName')
    for i in range(len(result)-1):
        print(result[i].get_text(strip=True),end=',')
    print(end='\n\n')