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

python requests+pyquery爬取猫眼top100

程序员文章站 2022-05-02 18:08:48
...
import requests
from pyquery import PyQuery as pq
import time
import json
def get_one_page(url):
    res=requests.get(url)
    return res.content.decode()

def parse_one_page(html):
    doc=pq(html)
    dd=doc('.board-wrapper dd')
    for item in dd.items():
        a=item.find('i').eq(0).text()
        b=item.find('.name>a').text()
        c=item.find('.star').text()
        d=item.find('.releasetime').text()
        e=item.find('.score i').eq(0).text()+item.find('.score i').eq(1).text()
        yield{
            '排名':a,
            '剧名':b,
            '主演':c[3:],
            '上映时间':d[5:],
            '评分':e
        }

def write_one_page(parse):
    with open('maoyan.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(parse,ensure_ascii=False)+'\n')


def main(offset):
    url='https://maoyan.com/board/4?offset='+str(offset)
    html=get_one_page(url)
    for parse in parse_one_page(html):
        print(parse)
        write_one_page(parse)

if __name__ == '__main__': 
    for i in range(10): 
        print('第%d页解析成功'%(i+1))
        main(i*10)
        time.sleep(2)