爬取微信公众号文章并发布到wordpress

# -*- coding:utf-8 -*-
import requests
import re
import time
import json
import random
import datetime
from wordpress_xmlrpc import Client, WordPressPost
from wordpress_xmlrpc.methods.posts import GetPosts, NewPost
from wordpress_xmlrpc.methods.users import GetUserInfo

# 公众号文章链接
url = 'http://mp.weixin.qq.com/s?xxxxxxxxxxx'

# 微信公众号文章爬取
def get_article(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        content = response.text
        # 标题
        title = re.findall(r'<title>(.*?)</title>', content)[0]
        # 内容
        content = re.findall(r'<div class="rich_media_content " id="js_content">(.*?)</div>', content, re.S)[0]
        content = re.sub(r'<.*?>', '', content)
        content = content.replace('&nbsp;', '').replace('\n', '').replace('\u3000', '')
        return title, content
    else:
        print('请求失败')

# 连接wordpress
wp = Client('http://www.example.com/xmlrpc.php', 'username', 'password')

# 发布文章
def post_article(title, content):
    post = WordPressPost()
    post.title = title
    post.content = content
    post.post_status = 'publish'
    post.terms_names = {
        'post_tag': ['Python', '爬虫'],
        'category': ['Python']
    }
    wp.call(NewPost(post))
    print('发布成功！')

if __name__ == '__main__':
    title, content = get_article(url)
    post_article(title, content)