抓取猫眼电影排行前一百

代码主要是大神写的：https://cuiqingcai.com/5534.html

需要看具体细节的去该网址：

import json
import requests
from requests.exceptions import RequestException
import re
import time

def get_one_page(url):            
    try:                                 ####一定要加Header，大神的没加，跑不起来
        header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 UBrowser/6.1.2107.204 Safari/537.36'}
        response = requests.get(url,headers=header)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):              #解析网页，获取想要的信息
    #print(html)
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                         + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
    #print(pattern)
    items = re.findall(pattern, html)
    #print(items)
    #exit()
    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2],
            'actor': item[3].strip()[3:],
            'time': item[4].strip()[5:],
            'score': item[5] + item[6]
        }

def write_to_file(content):                                 #写入TXT文件
    with open('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')

def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)    #offset值得是偏移量，每个
    html = get_one_page(url)                                #网页上面是十部电影，offset
    for item in parse_one_page(html):                       #下一页就是+10
        print(item)                                         #比较有规律，F12打开源码看看
        write_to_file(item)

if __name__ == '__main__':
    for i in range(10):                                      #这里就是遍历前十页
        main(offset=i * 10)
        time.sleep(1)