requests_猫眼电影

import re 
import os
import time
import random
import requests
import pandas as pd

# 方法一，用于网页翻页有规律的情况，如0,10,20,30,40
# 存储数据 
datalist = []

for i in range(11):  #爬取10页
    print('正在爬取第%s页'%i)
    url = 'https://maoyan.com/board/4?offset='+str(i*10)
    proxies = [{'http': 'http://58.212.42.116:36708'}, {'http':'http://117.57.91.53:9999'}, {'http':'123.169.35.184:9999'}]
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.42 Safari/537.36'
              ,'Connection': 'close'}
    
    response = requests.get(url, headers = header, proxies = random.choice(proxies))#verify是否验证服务器的SSL证书
    html = response.text

    # 正则表达式

    indregex = re.compile('<i class="board-index board-index-.*?">(.*?)</i>')
    ind = re.findall(indregex,html)

    titleregex = re.compile('<p class="name"><a href=.*?title=.*?data-act=.*?data-val=.*?>(.*?)</a></p>')
    title = re.findall(titleregex,html)

    nameregex = re.compile('<p class="star">\n\s+(.*?)\n\s+</p>')
    name = re.findall(nameregex,html)

    dateregex = re.compile('<p class="releasetime">(.*?)</p>')
    date = re.findall(dateregex,html)

    scoreregex = re.compile('<p class="score"><i class="integer">(.*?)</i><i class="fraction">(.*?)</i></p>')
    score = re.findall(scoreregex,html)
   
    # 循环保存数据
    for i in range(len(ind)):
        datalist.append([ind[i], title[i], name[i], date[i], float(''.join(score[i]))])
    time.sleep(random.randint(6,8))  # 设置间隔时间
df = pd.DataFrame(datalist,columns=['排名','电影名称','演员','上映日期','评分'])
df.to_csv('D:\\Desktop\\爬虫_anaconda\\猫眼TOP100.csv',index=False)
print('爬取完成,文件：猫眼TOP100.csv')

# 方法二，用于网页翻页没有规律的情况，直接从下一页按钮中获取第二页的信息
# 或者只有当前页和下一页的选项，没有显示一共有多少页


datalist = []
start = '0'
while True:
    try: #异常处理，使代码更加健壮
        print('正在爬取第%s页'%int(start))
        url = 'https://maoyan.com/board/4?offset='+start
        header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.42 Safari/537.36'}
        response = requests.get(url, headers = header)
        if response.status_code == 200:
            html = response.text

            #正则表达式

            indregex = re.compile('<i class="board-index board-index-.*?">(.*?)</i>')
            ind = re.findall(indregex,html)

            titleregex = re.compile('<p class="name"><a href=.*?title=.*?data-act=.*?data-val=.*?>(.*?)</a></p>')
            title = re.findall(titleregex,html)

            nameregex = re.compile('<p class="star">\n\s+(.*?)\n\s+</p>')
            name = re.findall(nameregex,html)

            dateregex = re.compile('<p class="releasetime">(.*?)</p>')
            date = re.findall(dateregex,html)

            scoreregex = re.compile('<p class="score"><i class="integer">(.*?)</i><i class="fraction">(.*?)</i></p>')
            score = re.findall(scoreregex,html)
            
            # 存储数据
            for i in range(len(ind)):
                datalist.append([ind[i], title[i], name[i], date[i], float(''.join(score[i]))])
            time.sleep(random.randint(6,8))
            
        startpattern  = re.compile('"?offset=(.*?)">下一页</a>')
        start = re.findall(startpattern,html)[0]
#         print(start)
    except:
        break
        print('爬虫报错')
        
df = pd.DataFrame(datalist,columns=['排名','电影名称','演员','上映日期','评分'])
df.to_csv('D:\\Desktop\\爬虫_anaconda\\猫眼TOP100.csv',index=False)
print('爬取完成')