@远方很远 from multiprocess import Process
import time
def func():
for i in range(10):
print( 子 ,i)
time.sleep(1)


if __name__== __main__ :
p=Process(target=func)
p.start()
for i in range(10):
print( 主 ,i)
time.sleep(1)

为什么开的这么难

你复制我得看看

我觉得我的模块有问题

import requests
import re
import json
import os
from requests.exceptions import RequestException
headers = {
     User-Agent :  Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36 ,
 Referer :  
https://maoyan.com ,
 Cookie :  __mta=150257545.1631492828404.1631494019461.1631494128206.11; uuid_n_v=v1; uuid=527644E0142911ECB55CBB305D2AA0B10206AFBAB4CB475088C931781076E1FA; _csrf=5e4a62b4751f4510de197b6bc0c95135582879125c178b5ff5f2ebd94019dba5; Hm_lvt_703e94591e87be68cc8da0da7cbd0be2=1631492828; _lx_utm=utm_source%3DBaidu%26utm_medium%3Dorganic; _lxsdk_cuid=17bdc8cea2dc8-00c198070d82d5-3e604809-15f900-17bdc8cea2ec8; _lxsdk=527644E0142911ECB55CBB305D2AA0B10206AFBAB4CB475088C931781076E1FA; __mta=150257545.1631492828404.1631492828404.1631492831171.2; Hm_lpvt_703e94591e87be68cc8da0da7cbd0be2=1631494128; _lxsdk_s=17bdc8cea2f-7eb-b35-003%7C%7C26 
}
# 对单页的网页源代码进行爬取
def get_one_page(url, headers):
    try:
        response = requests.get(url, headers=headers)#获取网页
        if response.status_code == 200:  #确认网页信息是不是200，200是正常的
            return response.text
        return None
    except RequestException:
        return None
#解析这个网页
#正则表达式提取信息
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]
        }
# 将信息写入文件
def write_to_file(content):
    # encoding = utf-8 ,ensure_ascii =False,使写入文件的代码显示为中文
    with open( result.txt ,  a , encoding= utf-8 ) as f:
        f.write(json.dumps(content, ensure_ascii=False) +  \n )
        f.close()
# 下载电影封面
def save_image_file(url, path):
    jd = requests.get(url)
    if jd.status_code == 200:
        with open(path,  wb ) as f:
            f.write(jd.content)
            f.close()
#主函数
def main(offset):
    url =  
https://maoyan.com/board/4?offset=  + str(offset)
    html = get_one_page(url, headers)
    if not os.path.exists( movieImgs ):
        os.mkdir( movieImgs )
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)
        save_image_file(item[ image ],  movieImgs/  + item[ title ] +  .jpg )
if __name__ ==  __main__ :
    # 对每一页信息进行爬取
    for i in range(10):
        main(i*10)

那我应该从哪里加，不知道从哪继续爬

正则建议全部换了，用lxml

一般我用的

    r1=requests.get(url=urls,headers=headers(),verify=False)
    r1=r1.content.decode( gbk ,errors= ignore )
    obj1=etree.HTML(r1)
    soup=BeautifulSoup(r1, lxml )
    标题=obj1.xpath( //*[@id= content ]/div[1]/h1/text() )

标题就直接出来了

 nexturls=obj1.xpath( //*[@id= content ]/div[1]/div/a[3]/@href )
 nexturls=starturl+nexturls[0]
 r2=requests.get(url=nexturls,headers=headers(),verify=False)
 r2=r2.content.decode( gbk ,errors= ignore )

开始第二层爬取，另外单个爬取效率太低了，建议建立header池

外加使用多线程，我爬个小说用了一个多小时

我的妈呀哈哈哈，我得好好研究了

应数专业已经哭了

还要建立UA池，代理IP池