requests.get发送请求得到回应(headers模拟浏览器),
注意查看res.status_code是否返回200,res.encoding是否与网页charset一致,res.text查看内容
soup解析网页内容,因为在一个页面中就能获取信息,先找能涵盖信息的大标签,再在大标签下提取小标签
字符串处理主要用到strip,split,join
# -*- coding: utf-8 -*-
"""
Created on Thu Jul 26 18:41:06 2018
@author: MyPC
"""
import requests
from bs4 import BeautifulSoup
#url='https://movie.douban.com/top250'
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 \
(KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
total=[]
def getinfo(url):
res=requests.get(url,headers=headers)
soup=BeautifulSoup(res.text,'html.parser')
all=soup.find_all('div',class_='info')
for each in all:
biaoti=each.find('span',class_='title').string
daoyan=each.find('div',class_='bd').p.text.split('\n')[1].strip()
nianfen=each.find('div',class_='bd').p.text.split('\n')[2].strip()
pingfen=float(each.find('span',class_='rating_num').text)
try:
jianjie=each.find('span',class_='inq').text
except:
jianjie=''
info={'标题':biaoti,
'导演':daoyan,
'年份':nianfen,
'评分':pingfen,
'简介':jianjie}
total.append(info)
return total
if __name__ == '__main__':
for i in range(10):
URL='https://movie.douban.com/top250?start={}&filter='.format(25 * i)
getinfo(URL)
import pandas
dd=pandas.DataFrame(total)
dd.to_excel('douban250.xls',columns=['标题','年份','评分','导演','简介'])