换坑季-51Job前程无忧 Python爬虫

写了个简易的Python爬虫，实现对目的工作的分析。
说明，只用了正则re库进行数据处理，requests进行请求,开了4个简易的函数线程。
url是以下界面的url：

主要实现了以下CSV功能：

全部代码：

import requests
import re
import csv
from threading import Threaddef req(i):count = 1try:for url in i:headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}response = requests.get(url=url, headers=headers, timeout=5)response.encoding = 'GBK'content = re.findall(r'<a target="_blank" title="(.*?)" href="(.*?)" onmousedown="">.*?<span class="t2"><a target="_blank" title="(.*?)" href=".*?">.*?</a></span>.*?<span class="t3">(.*?)</span>.*?<span class="t4">(.*?)</span>.*?<span class="t5">(.*?)</span>', response.text, re.S)# print(content)for index in content:txt = []title = index[0]thisUrl = index[1]try:thisContent = requests.get(url=thisUrl, headers=headers, timeout=5)text = re.findall(r'<div class="bmsg job_msg inbox">(.*?)<div class="mt10">', thisContent.text, re.S)final = ''.join(text).replace('\r\n\t\t\t\t\t\t', '').replace('<p>', '').replace('</p>', '').replace('<span>', '').replace('</span>', '').replace('<br>', '').replace('&nbsp;', '').replace('</div>', '').replace('<div>', '').replace('\t\t\t\t\t\t\t\t\t\t\t\t', '').replace('<b>', '').replace('</b>', '').replace('</li>', '').replace('</strong>', '').replace('<strong>', '').replace('<li>', '')company = index[2]area = index[3]salary = index[4]date = index[5]txt.append(title)txt.append(thisUrl)txt.append(final)txt.append(company)txt.append(area)txt.append(salary)txt.append(date)# print(txt)with open(r'./前程无忧.csv', 'a', newline='', encoding='utf-8-sig') as csvf:spanwriter = csv.writer(csvf)spanwriter.writerow(txt)count = count + 1except:print("此次请求详情失败！！！" + thisUrl)except:print('请求首页失败！' + i)print("共%d多少条信息~" % count)if __name__ == '__main__':txt1 = []txt2 = []txt3 = []txt4 = []url = 'https://search.51job.com/list/090200,000000,0000,00,9,99,%25E8%25BF%2590%25E7%25BB%25B4%25E5%25B7%25A5%25E7%25A8%258B%25E5%25B8%2588,2,{}.html?lang=c&stype=1&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare='for i in range(1, 6):i = url.format(i)txt1.append(i)for j in range(6, 12):j = url.format(j)txt2.append(j)for k in range(12, 18):k = url.format(k)txt3.append(k)for k in range(18, 24):k = url.format(k)txt3.append(k)t1 = Thread(target=req, args=(txt1,))t1.start()print('t1线程开始！')t2 = Thread(target=req, args=(txt2,))t2.start()print('t2线程开始！')t3 = Thread(target=req, args=(txt3,))t3.start()print('t3线程开始！')t4 = Thread(target=req, args=(txt4,))t4.start()print('t4线程开始！')

上面这个开了4个线程的代码其实对爬虫还是不太友好。
以下代码可以在详细页进行爬虫，建议使用生产者消费者模式。

import re
import requestsurl = 'https://jobs.51job.com/chengdu-jjq/114069603.html?s=01&t=0'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}
response = requests.get(url=url, headers=headers, timeout=5)
response.encoding = 'GBK'
# 工作职位
job = re.findall(r'<h1 title="(.*?)">', response.text)
print(job)
# 薪资
salary = re.findall(r'<h1 title=".*?">.*?<input value="\d+" name="hidJobID" id="hidJobID" type="hidden" jt="0">.*?<strong>(.*?)</strong>', response.text, re.S)
print(salary)
# 公司名称
company = re.findall(r'target="_blank" title="(.*?)" class="catn">', response.text)
print(company)
# 公司性质
flag = re.findall(r'<p class="at" title="(.*?)"><span class="i_flag"></span>.*?</p>', response.text)
print(flag)
# 公司规模
people = re.findall(r'<p class="at" title="(.*?)"><span class="i_people"></span>.*?</p>', response.text)
print(people)
# 职位详细的内容：
content = re.findall(r'<p class="msg ltype" title="(.*?)">.*?</p>', response.text, re.S)
# 将正则匹配的内容进行字符串处理
content_str = ''.join(content)
# 城市
txt_city = re.findall(r'.*?(成都.*?)&nbsp.*?', content_str)
print(txt_city)
# 招多少人
txt_count = re.findall(r'.*?(招\d人).*?', content_str)
print(txt_count)
# 经验
txt_experience = re.findall(r'.*?(无工作经验).*?', content_str)
if len(txt_experience) == 0:txt_experience = re.findall(r'.*?(\d+年经验).*?', content_str)
print(txt_experience)
# 发布日期
txt_date = re.findall(r'.*?(\d+-\d+发布).*?', content_str)
print(txt_date)
# 学历要求， 只匹配了大专和本科
txt_education = re.findall(r'.*?(本科).*?', content_str)
if len(txt_education) == 0:txt_education = re.findall(r'.*?(大专).*?', content_str)
else:txt_education = '无学历要求'
print(txt_education)
# 职位招聘要求内容描述：
descrition = re.findall(r'<div class="bmsg job_msg inbox">(.*?)<div class="mt10">', response.text, re.S)
descrition = ''.join(descrition).replace('\r\n\t\t\t\t\t\t', '').replace('<p>', '').replace('</p>', '').replace('<span>', '').replace('</span>', '').replace('<br>', '').replace('&nbsp;', '').replace('</div>', '').replace('<div>', '').replace('\t\t\t\t\t\t\t\t\t\t\t\t', '').replace('<b>', '').replace('</b>', '').replace('</li>', '').replace('</strong>', '').replace('<strong>', '').replace('<li>', '')
print(descrition)