python之简单爬取一个网站信息

import requests
from bs4 import BeautifulSoup

r=requests.get(‘http://www.baidu.com‘)
r.encoding=None
result=r.text
bs=BeautifulSoup(result,‘html.parser‘)
print(bs.title)
print(bs.title.text)

import requests
from bs4 import BeautifulSoup

#用来解决乱码现象，所以编写爬取信息的代码最好带上（输出出现乱码或者UnicodeEncodeError：‘gbk‘codec can‘t encode character）  
import io      
import sys
sys.stdout = io.TextIOWrapper(sys.stdout.buffer,encoding=‘gb18030‘)


#用来防止反爬取，可以了解一下
headers={"User-Agent" : "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.6)",
　　"Accept" : "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
　　"Accept-Language" : "en-us",
　　"Connection" : "keep-alive",
　　"Accept-Charset" : "GB2312,utf-8;q=0.7,*;q=0.7"
}


#获取51job网站的基本信息
r=requests.get(‘https://search.51job.com/list/000000,000000,0000,00,9,99,python,2,1.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99&degreefrom=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=‘)
r.encoding=r.apparent_encoding
result=r.text
bs=BeautifulSoup(result,‘html.parser‘)
print(bs.prettify())

u1=bs.find_all(‘u1‘,attrs={‘class‘:‘item_con_list‘})    #这部分代码便是我们爬取的目标，51job网站上关于python职业的薪资
print(len(u1))
li=bs.find_all(‘span‘,attrs={‘class‘:‘t4‘})
for l in li:
    print(l.text)