requests BeautifulSoup 猫眼电影信息的爬取

**

根据用户需要爬取的数量，爬取猫眼电影网的电影信息

**

import requests
from requests.exceptions import RequestException
from bs4 import BeautifulSoup
import json,os,sys
import lxml
from multiprocessing import Pool

filename = os.path.abspath(__file__)#D:\tools\JetBrains\wk\PC\pcfile\PcForMaoYanTop.py
result_path = os.path.dirname(os.path.dirname(filename))#D:\tools\JetBrains\wk\PC

def get_one_page(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
        }
        response = requests.get(url,headers=headers)
        if response.status_code == 200:
            return  response.text
        else:
            return None
    except RequestException:
        print('请求连接失败')
        return None


def parse_html(html):
    soup = BeautifulSoup(html,'lxml')
    print(soup.prettify())
    items = soup.find_all('dd')
    for item in items:
        yield {
            'index' : item.i.string,
            'title' : item.find(class_='name').string,
            'img' : item.find(class_='board-img')['data-src'],
            'star' : item.find(class_='star').string.strip()[3:],
            'time' : item.find(class_='releasetime').string.strip()[5:],
            'score' : item.find(class_='integer').string.strip()+item.find(class_='fraction').string.strip()
        }

def write_to_file(content):
    url = result_path+'\pcresult\maoYan.txt'
    with open(url,'a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n')
        f.close()

def write_img(content):
    for i in range(len(content)):
        url = result_path+'\pcresult\\'+str(content['title'])+'.jpg'
        print(content['img'])
        with open(url,'ab') as f:
            resp = requests.get(content['img']).content
            f.write(resp)
            f.close()

def main(offset):
    url = 'https://maoyan.com/board/4?offset='+str(offset)
    html = get_one_page(url)
    text = parse_html(html)
    for i in text:
        write_to_file(i)
        write_img(i)

if __name__ == '__main__':
    a = input("请输入要爬取多少页")
    a = int(a)
    pool = Pool()
    pool.map(main,[i*10 for i in range(a)])