用BeautifulSoup 爬取求职网站信息(成功)

---

requests在爬取网页时候时候中文显示乱码

res.encoding #获取res的编码格式

res.apparent_encoding #获取网页正确的编码格式

---

源码：

import requests

from bs4 import BeautifulSoup

l=[]

name=[]

com=[]

salary=[]

url='https://search.51job.com/list/000000,000000,0000,00,9,99,%2520,2,1.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&providesalary=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare='

res=requests.get(url)

res.encoding = res.apparent_encoding

soup = BeautifulSoup(res.text, 'html.parser')

divs1=soup.select("p.t1")

divs2=soup.select("span.t2")

divs3=soup.select("span.t4")

#print(divs)

for div in divs1[:]:

    name1=div.select("span>a")[0].text.strip()

    name.append(name1)

for div in divs2[1:]:

    com1=div.select("a")[0].text.strip()

    com.append(com1)   

for div in divs3[1:]:

    salary1=div.text.strip()

    salary.append(salary1)

for i in range(len(name)):

    l.append([name[i],com[i],salary[i]])

for i in l:

    print(i)