猫眼电影排行信息

猫眼电影排行信息

python

import requests
from pyquery import PyQuery as pq
import json

#获取网页源码
def getPage(url):
    headers={
        'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
    }
    response = requests.get(url,headers=headers)
    if response.status_code==200:
        return response.text
    else:
        return None

#解析页面
def parsePage(html):
    list=[]
    doc=pq(html)
    items=doc('dd').items()
    for item in items:
        #排名
        ranking=item('.board-index').text()
        #图片
        img=item('.board-img').attr('data-src')
        #标题
        title=item('.name a').text()
        #演员
        actor=item('.star').text()
        actor=actor.replace('主演：','')
        #评分
        score=item('.score').text()
        #date
        showTime=item('.releasetime').text().replace('上映时间：','')
        info={'排名':ranking,'图片':img,'标题':title,'演员':actor,'评分':score,'上映时间':showTime}
        list.append(info)
    return list

#文件写入
def writeToFile(content):
    with open('F:\\topTen.txt','a') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n--------------------------------------------------------------------\n')


def main(offset):
    url = 'https://maoyan.com/board/4?offset=' + str(offset) #  url = 'https://maoyan.com/board/4?offset=' + str(offset)
    html = getPage(url)

    items = parsePage(html)
    for item in items:
        writeToFile(item)
        print(item)

for page in range(0,10):
    offset = page * 10
    main(offset)