IMDB TOP 250爬虫
这个小学期Python大作业搞了个获取IMDB TOP 250电影全部信息的爬虫。第二次写爬虫,比在暑假集训时写的熟练多了。欢迎大家评论。
附上代码
'''
************************************************
*Made by 1120162015 李博
* 1120161966 张嘉熙
*Time:2017.9.11
*Target:All movies' information of IMDB TOP_250
*Resources:http://www.imdb.cn/IMDB250/
*纯原创 转载请注明作者:李博,张嘉熙
************************************************
'''
import re
import requests
import numpy as np
import matplotlib.pyplot as plt
from bs4 import BeautifulSoup
num = 1 #电影计数
All_txt = [] #全部电影的信息
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'}#浏览器代理
def getHTMLText(url):
try:
#print(url)
r = requests.get( url,headers = headers )
#print(r)
r.encoding = 'utf-8'
return r.text
except:
return "错误"
#从每一部电影的页面中获取全部信息
def get_all_information(url,page):
global num,All_txt
txt = getHTMLText(url)
if txt != "错误":
print('page'+str(page)+' NO.'+str(num)+' Get it!')
if num == 247:
print('Finished!!!')
soup = BeautifulSoup(txt,"html.parser")
Cname,Ename,Score,title,Actor,Starring,Infor = '','','','','','',''
#TOP250-film_Chinese_name&Score
infor_1 = soup.find_all('div',class_ = 'hdd')
rel =