使用BeautifuSoup4解析器，将招聘网页上的招聘单位名称存储出来。其他信息可类似爬取即可
# -*- coding:utf-8 -*-from bs4 import BeautifulSoup
import urllib2
import json # 使用了json格式存储def csdn():
url = 'https://job.csdn.net/search/index'
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
request = urllib2.Request(url, headers=headers)
response = urllib2.urlopen(request)
resHtml = response.read()
output = open('csdnJob.json', 'w')
soup = BeautifulSoup(resHtml, 'html.parser', from_encoding='utf-8')
# 创建CSS选择器
result = soup.select('div[class="position_list clearfix"]')
# result += result2
print("----")
print (result)
items = []
for site in result:
item = {}
print (site)
name = site.select('a[class="enterprise_name"]')[0].get_text()
item['name'] = name
items.append(item) # 禁用ascii编码，按utf-8编码
line = json.dumps(items, ensure_ascii=False) output.write(line.encode('utf-8'))
output.close()if __name__ == "__main__":
csdn()
效果：
