【python实操】年轻人，想会写抢购脚本和爬虫？试试多线程吧（附爬虫完整源代码）

def thread_func(args):
    # 线程要执行的操作

import requests
import threading

def download(url, filename):
    # 下载文件
    content = requests.get(url).content
    with open(filename, "wb") as f:
        f.write(content)

if __name__ == '__main__':
    urls = ["http://example.com/file1", "http://example.com/file2", "http://example.com/file3"]
    filenames = ["file1.txt", "file2.txt", "file3.txt"]
    threads = []
    for i in range(3):
        t = threading.Thread(target=download, args=(urls[i], filenames[i]))
        threads.append(t)
    
    # 启动多线程
    for t in threads:
        t.start()
        
    # 等待所有线程完成
    for t in threads:
        t.join()

import requests
import threading
from bs4 import BeautifulSoup

def parse_page(url):
    # 下载页面
    content = requests.get(url).content
    soup = BeautifulSoup(content, "html.parser")
    # 解析页面
    results = soup.find_all("div", class_="result")
    return results

if __name__ == '__main__':
    urls = ["http://example.com/page1", "http://example.com/page2", "http://example.com/page3"]
    threads = []
    for url in urls:
        t = threading.Thread(target=parse_page, args=(url,))
        threads.append(t)
    
    # 启动多线程
    for t in threads:
        t.start()
        
    # 合并结果
    results = []
    for t in threads:
        results += t.join()

import requests
from bs4 import BeautifulSoup
import csv

# 定义要爬取的页面URL
url = 'https://movie.douban.com/top250'

# 发送HTTP请求获取页面内容
response = requests.get(url)

# 使用BeautifulSoup解析HTML页面
soup = BeautifulSoup(response.text, 'html.parser')

# 遍历每个电影条目，并提取电影信息
movies = []
for li in soup.find_all('li', class_='item'):
    # 获取电影名称
    name = li.find('span', class_='title').text
    # 获取电影评分
    rating = li.find('span', class_='rating_num').text
    # 获取电影导演和演员
    info = li.find('div', class_='bd').p.text.strip().split('\n')[0]
    # 提取导演和演员信息
    director = info.split(':')[0]
    actors = [x.strip() for x in info.split(':')[1].split('/')]
    # 将电影信息添加到列表中
    movies.append([name, rating, director, actors])

# 将电影信息保存到CSV文件中
with open('douban_movies.csv', 'w', newline='', encoding='utf-8') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(['电影名称', '评分', '导演', '演员'])
    writer.writerows(movies)

print('豆瓣电影Top250信息已保存到douban_movies.csv文件中。')

import requests
from lxml import etree
import csv
import time


class DoubanSpider(object):
    def __init__(self):
        self.header = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36'
        }

    # 发请求 获响应
    def get_source(self, com_url):
        res = requests.get(com_url, headers=self.header)
        html = res.content.decode('utf-8')
        return html

    # 解析数据
    def parsed_source(self, html):
        tree = etree.HTML(html)
        divs = tree.xpath('//div[@class="info"]')
        # print(divs)
        lis_data = []
        for div in divs:
            d = {}
            # 标题
            title = div.xpath('./div[@class="hd"]/a/span/text()')[0].strip()
            # print(title)
            # 评分
            score = div.xpath('./div[@class="bd"]/div[@class="star"]/span[@class="rating_num"]/text()')[0].strip()
            # print(score)
            # 评价人数
            evaluate = div.xpath('./div[@class="bd"]/div[@class="star"]/span[last()]/text()')[0].strip()
            # print(evaluate)
            # 引用
            quote = div.xpath('./div[@class="bd"]/p[@class="quote"]/span/text()')
            if quote:
                quote = quote[0]
            else:
                quote = ''
            # 电影链接url
            link_url = div.xpath('./div[@class="hd"]/a/@href')[0].strip()
            # print(link_url)
            # 根据key值提取数据
            d['title'] = title
            d['score'] = score
            d['evaluate'] = evaluate
            d['quote'] = quote
            d['link_url'] = link_url
            lis_data.append(d)
        # print(lis_data)
        return lis_data

    # 保存数据
    def save_source(self, move_data, header):
        with open('movie_data.csv', 'a', encoding='utf-8-sig', newline='') as f:
            w = csv.DictWriter(f, header)
            # 写入表头
            w.writeheader()
            # writerows 一次性写入多行数据
            w.writerows(move_data)

    # 主函数
    def main(self):
        start = int(input('输入要爬取的起始页：'))
        end = int(input('输入要爬取的末尾页：'))
        for i in range(start, end+1):
            time.sleep(2)
            page = (i-1) * 25
            com_url = 'https://movie.douban.com/top250?start=' + str(page)
            h = self.get_source(com_url)
            # print(h)
            print('爬虫机器人正在爬取第%d页' % i)
            move_data = self.parsed_source(h)
            # 设置表头
            header = ['title', 'score', 'evaluate', 'quote', 'link_url']
            # print(move_data)
            self.save_source(move_data, header)


if __name__ == '__main__':
    # 实例化对象
    Spider = DoubanSpider()
    # 主函数调用
    Spider.main()

================
|				|
|				|
|===============

从此讨厌编程，不想继续学下去。每次作业应付。
算法考试，数据结构考试随便背代码，只求通过。
最后呢？我学会变成了吗？只能对一些概念侃侃而谈，但真的会几行代码，能写出实用工具吗？
答案变得模糊。
所以我们要从现在开始，学好python，不要再糊弄下去！！！