利用requests库和bs4实现，demo如下：
#coding:utf-
import requests
from bs4 import BeautifulSoup
import bs4
import re
headers = {
'User-Agent':'Chrome/68.0.3440.106'
} def getHTMLText(url):
try:
r=requests.get(url,headers=headers)
r.raise_for_status()
r.encoding=r.apparent_encoding
return r.text
except:
return ''
'''
def getHref(html):
soup=BeautifulSoup(html,'lxml')
for node in soup.find_all()
'''
def bdurlCode(url):
res = requests.get(url, allow_redirects=False)
Real_url = res.headers['location']
return Real_url def fillList(ulist,html):
soup=BeautifulSoup(html,'lxml')
for node in soup.find_all('div', {'class': 'result c-container '}):
abstract_node = node.find('div',{'class':'c-abstract'})
cite_node = node.find('a', {'class': 'c-showurl'})
time_node=node.find('span',{'class':' newTimeFactor_before_abs m'})
if not time_node:continue
url=cite_node['href']
url=bdurlCode(url)
abstract=abstract_node.text
time=time_node.text
ulist.append([url,time,abstract])
print(ulist)
print(len(ulist)) uinfo=[]
url="https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=baidu&wd=%E6%98%8E%E7%95%A5%E6%95%B0%E6%8D%AECTO&oq=%25E6%2598%258E%25E7%2595%25A5%25E6%2595%25B0%25E6%258D%25AE&rsv_pq=9429009d00000f0c&rsv_t=0278viP4h51Y2xMneo8a0HfaOkqnhW8wmti1KAz4ddKuKCUjeKDsh9yB1YM&rqlang=cn&rsv_enter=1&inputT=894&rsv_sug3=17&rsv_sug1=9&rsv_sug7=100&rsv_sug2=0&rsv_sug4=1273&rsv_sug=1"
html=getHTMLText(url)
fillList(uinfo,html)