python多线程爬取图片并通过数据库发布到wordpress文章的代码

import requests
import threading
import pymysql

# 定义爬取图片的函数
def get_img(url):
    r = requests.get(url)
    with open('img.jpg', 'wb') as f:
        f.write(r.content)

# 定义发布文章的函数
def post_article(title, content):
    # 连接数据库
    conn = pymysql.connect(host='localhost', user='root', password='123456', db='wordpress', charset='utf8')
    cursor = conn.cursor()
    # 插入文章
    sql = "INSERT INTO wp_posts (post_author, post_date, post_date_gmt, post_content, post_title, post_status, comment_status, ping_status, post_name, post_modified, post_modified_gmt, post_type) VALUES (1, now(), now(), %s, %s, 'publish', 'open', 'open', %s, now(), now(), 'post')"
    cursor.execute(sql, (content, title, title))
    post_id = cursor.lastrowid
    # 插入图片
    sql = "INSERT INTO wp_posts (post_author, post_date, post_date_gmt, post_content, post_title, post_status, comment_status, ping_status, post_name, post_modified, post_modified_gmt, post_type) VALUES (1, now(), now(), '', 'img.jpg', 'inherit', 'open', 'open', 'img.jpg', now(), now(), 'attachment')"
    cursor.execute(sql)
    img_id = cursor.lastrowid
    # 更新图片的post_parent
    sql = "UPDATE wp_posts SET post_parent = %s WHERE ID = %s"
    cursor.execute(sql, (post_id, img_id))
    # 提交
    conn.commit()
    # 关闭连接
    cursor.close()
    conn.close()

# 定义爬取图片并发布文章的函数
def spider_and_post(url, title, content):
    # 创建线程
    t1 = threading.Thread(target=get_img, args=(url,))
    t2 = threading.Thread(target=post_article, args=(title, content))
    # 启动线程
    t1.start()
    t2.start()
    # 等待线程结束
    t1.join()
    t2.join()

if __name__ == '__main__':
    url = 'http://www.example.com/img.jpg'
    title = '文章标题'
    content = '文章内容'
    spider_and_post(url, title, content)

不通过数据库的方式

import requests
import threading
import time
from bs4 import BeautifulSoup

# 定义一个全局变量，用来存放爬取到的图片地址
img_urls = []

# 定义一个函数，用来爬取图片
def get_img_urls(url):
    # 请求网页
    response = requests.get(url)
    # 解析网页
    soup = BeautifulSoup(response.text, 'lxml')
    # 找到所有的图片
    imgs = soup.find_all('img')
    # 遍历图片，获取图片的地址
    for img in imgs:
        img_url = img['src']
        # 将图片地址添加到全局变量中
        img_urls.append(img_url)

# 定义一个函数，用来发布文章
def post_article(img_urls):
    # 定义文章标题
    title = '爬取图片并发布到wordpress文章'
    # 定义文章内容
    content = '<h1>爬取图片并发布到wordpress文章</h1>'
    # 遍历图片地址，拼接文章内容
    for img_url in img_urls:
        content += '<img src="{}">'.format(img_url)
    # 发布文章
    # 这里省略发布文章的代码

# 定义一个函数，用来启动多线程
def main():
    # 定义要爬取的网页地址
    urls = ['http://www.example.com/1.html', 'http://www.example.com/2.html', 'http://www.example.com/3.html']
    # 创建线程列表
    threads = []
    # 遍历网页地址，创建并启动线程
    for url in urls:
        t = threading.Thread(target=get_img_urls, args=(url,))
        threads.append(t)
        t.start()
    # 等待所有线程执行完毕
    for t in threads:
        t.join()
    # 发布文章
    post_article(img_urls)

if __name__ == '__main__':
    main()