欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

猫眼电影爬取

程序员文章站 2022-05-02 16:55:33
...
#!usr/bin/env python
#-*- encoding:utf-8 -*-
import requests
import re
from requests.exceptions import  RequestException
from flask import json
from multiprocessing import Pool
def get_one_page(url):
    header = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36'
    }
    try:
        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):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
    items = re.findall(pattern,html)
    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):
    with open('E:/getdata/result.csv','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+ '\n')
        f.close()
def main(offset):
    url = 'http://maoyan.com/board/4?offset='+str(offset)

    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)


if __name__=='__main__':
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])


相关标签: 爬虫