pip install wechatsogou --upgrade

pip install pdfkit

import os
import pdfkit
import datetime
import wechatsogou
# 初始化API
ws_api = wechatsogou.WechatSogouAPI(captcha_break_time=3)
def url2pdf(url, title, targetPath):
 '''
 使用pdfkit生成pdf文件
 :param url: 文章url
 :param title: 文章標題
 :param targetPath: 存儲pdf文件的路徑
 '''
 try:
 content_info = ws_api.get_article_content(url)
 except:
 return False
 # 處理后的html
 html = f'''
{title}
 {content_info['content_html']}
 
 '''
 try:
 path_wk="E:/softwareAPP/wkhtmltopdf/bin/wkhtmltopdf.exe";
 config=pdfkit.configuration(wkhtmltopdf=path_wk)
 pdfkit.from_string(input=html, output_path=targetPath,configuration=config)
 except:
 # 部分文章標題含特殊字符，不能作為文件名
 filename = datetime.datetime.now().strftime('%Y%m%d%H%M%S') + '.pdf'
 pdfkit.from_string(html, targetPath + os.path.sep + filename)
 
if __name__ == '__main__':
 # 此處為要爬取公眾號的名稱
 url2pdf("https://mp.weixin.qq.com/s/wwT5n2JwEEAkrrmOhedziw", "HBase的系統(tǒng)架構(gòu)全視角解讀","G:/test/hbase文檔.pdf" )
 # gzh_name = ''
 # # 如果不存在目標文件夾就進行創(chuàng)建
 # if not os.path.exists(targetPath):
 # os.makedirs(targetPath)
 # # 將該公眾號最近10篇文章信息以字典形式返回
 # data = ws_api.get_gzh_article_by_history(gzh_name)
 # article_list = data['article']
 # for article in article_list:
 # url = article['content_url']
 # title = article['title']
 # url2pdf(url, title, targetPath)