[Python知识库]python使用多线程进行爬豆瓣电影top250海报图片，附源码加运行结果

使用多线程进行爬豆瓣电影top250海报图片

# -- coding: UTF-8 --
import time
import requests
import urllib.request
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor, wait, ALL_COMPLETED

# 该函数用于下载图片
# 传入函数： 网页的网址url
def download_picture(url):
    headers = {
        "Host": "movie.douban.com",
        "Referer": "https://movie.douban.com/top250?start=225&filter=",
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36",
        }
    # 获取网页的源代码
    r = requests.get(url,headers=headers)
    # 利用BeautifulSoup将获取到的文本解析成HTML
    soup = BeautifulSoup(r.text, "lxml")
    # 获取网页中的电影图片
    content = soup.find('div', class_='article')
    images = content.find_all('img')
    # 获取

开通VIP 解锁文章