多进程爬取豆瓣电影出现异常

Question

完整代码如下

#多进程爬取豆瓣TOP250
import requests
from bs4 import BeautifulSoup
import time
from multiprocessing import Process,Queue


def open_url(url):
    proxies = {'http':'121.230.210.200:3256','http':'203.82.253.47:80','http':'118.117.189.17:3256'}
    headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36 Edg/92.0.902.62'}
    html = requests.get(url,headers = headers,proxies = proxies).text
    return html
    
def parse_url(url):
    html = BeautifulSoup(open_url(url),features="html.parser")
    
    #获取每一页所有电影名
    movies = []
    targets = html.find_all('span',class_="title")
    for each in targets:
        movies.append(each.text)
    
    #获取每一页所有电影得分
    marks = []
    targets = html.find_all('span',class_="rating_num",property="v:average")
    for each in targets:
        marks.append(each.text)
    
    #将数据储存到队列中
    for i in range(len(movies)):
        dataqueue.put(movies[i]+'  mark：'+marks[i])
        
    
    

def main():
    start_t = time.time()
    num = 1
    dataqueue = Queue()
    process_list = []
    
    #循环创建10个进程
    for i in range(10):
        url = 'https://movie.douban.com/top250?start=%d&filter=' % i*25
        process = Process(target = parse_url,args = url)
        process.start()
        process_list.append(process)
    
    #父进程等待所有子进程结束再进行下面的语句
    for process in process_list:
        process.join()
    
    #输出内容
    while not dataqueue.empty():
        print('排名：',num,'  title：',dataqueue.get())
        num+=1
        
    end_t = time.time()
    print('用时：',end_t - start_t)

if __name__ == '__main__':
    main()

但是每次运行都会报错，每一个进程都会出现以下异常

Traceback (most recent call last):
Traceback (most recent call last):
  File "D:\下载\python\lib\multiprocessing\process.py", line 313, in _bootstrap
    self.run()
  File "D:\下载\python\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
TypeError: parse_url() takes 1 positional argument but 1175 were given

为什么会出现如此多参数
该怎样解决

Answer 1

Process(target = parse_url,args = url) 这里的args 参数需要是一个元组形式，可以写成args=（url，）