使用python3爬取boss直聘

#目标url:https://www.zhipin.com/c101280100-p100109/?ka=search_100109
#爬取boss直聘上广州的python岗位
#这里就不实现爬取全部页面的了，想学的朋友看我之前的文章

import requests
from bs4 import BeautifulSoup


headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'}
url = 'https://www.zhipin.com/c101280100-p100109/?ka=search_100109'
urls = requests.get(url, headers=headers).text
soup = BeautifulSoup(urls, 'lxml')
#print(soup.prettify())

name = [] #公司名
for i in soup.find_all('div',class_="job-primary"):
	for y in i.find_all(class_="company-text"):
		for q in y.find_all('h3'):
			name.append(q.get_text())
#print(name)

post = [] #岗位
for i in soup.find_all('div', class_="job-title"):
	post.append(i.get_text())
#print(post)

salary = [] #薪资
for i in soup.find_all('span', class_="red"):
	salary.append(i.get_text())
#print(salary)

address = [] #地址
for i in soup.find_all(class_="info-primary"):
	for y in i.find_all('p'):
		address.append(y.get_text())
#print(address)

for q,w,e,r in zip(name,post,salary,address):
	print('公司名：',q)
	print('岗位：',w, end=' ')
	print('薪资：',e)
	print('地址：',r)
	print('-'*40)

运行结果：看一部分的