python豆瓣电影top250信息爬取

尝试使用了一次多进程，但是显示效果其实其实不是很好，不想用就去掉吧 

#!/usr/bin/env python
#-*- coding:utf-8 -*-

# file:豆瓣电影.py
# author:ytytyt
# datetime:2021/7/14 16:00
# software: PyCharm
'''
分析:
url:https://movie.douban.com/top250?start=0
每25部电影一页 start+25即翻页
数据位置:ol li(class grid_view)里面div(item),里面有div(pic)存放排名（em）,超链接里面有图片

'''
# import module your need
import requests
from requests.exceptions import RequestException
from pyquery import PyQuery as pq
import json,time
import multiprocessing

def getpage(url):
    headers={
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36'
    }
    try:
        res = requests.get(url,headers=headers)
        if res.status_code == 200:
            res.encoding="utf-8"
            return res.text
        else:
            return None
    except RequestException as e:
        print(e)
        return None

def parsePage(html):
    """解析爬取的内容"""
    doc = pq(html)
    res = doc(".item")
    #拿到电影相关的文本
    for data in res.items():
        #循环用解析出来的data创建解析器
        doc2 = pq(data)
        result ={
            "index" : doc2('.pic em').text(),
            "title" : doc2('.pic a img').attr.alt,
            "image" : doc2('.pic a img').attr.src,
            "info" : doc2('.info .bd p:first').text().replace(u'\xa0', u' ')
        }
        yield  result


def writeFile(content):
    """写入文件中"""

    with open("豆瓣top250.txt","a",encoding='utf-8') as file1:
        content = json.dumps(content, ensure_ascii=False) + "\n"
        file1.write(content)


def main(start,Lock):
    """主爬虫调度"""
    #两个爬虫一起工作
    for i in range(5):
        url = "https://movie.douban.com/top250?start="+str(start+25*i)
        print("正在爬取第{}页...".format((start+25*i)/25+1))
        html = getpage(url)
        if html:
            res = parsePage(html=html)
            for item in res:
                with Lock:
                    writeFile(item)



if __name__ == '__main__':
    #多进程实现(需用锁)
    mutex = multiprocessing.Lock()

    multiprocessing.Process(target=main,args=(0,mutex)).start()
    multiprocessing.Process(target=main,args=(125,mutex)).start()

    print("爬取完成")