capture-wechat.py

# update: 2019-5-11
import sys
import os
import time
from bs4 import BeautifulSoup
import requests
import pdfkit

def main(url):
    output_path = ...
    sys.path.append('/usr/local/bin/')
    r = requests.get(url)
    soup = BeautifulSoup(r.text, 'html.parser')
    title = soup.find('h2').text.strip()
    all_image = soup.find_all('img')
    for img in all_image:
        if img.has_attr('data-src'):
            img['src'] = img['data-src']
    host = 'mp.weixin.qq.com'
    pathname = url.replace('https://', '').replace(host, '')
    content = str(soup).replace('windows.location.href', url)\
                        .replace('location.href', url)\
                        .replace('windows.location.search', '')\
                        .replace('location.search', '')\
                        .replace('windows.location.protocol', 'https:')\
                        .replace('location.protocol', 'https:')\
                        .replace('windows.location.pathname', pathname)\
                        .replace('location.pathname', pathname)\
                        .replace('windows.location.host', host)\
                        .replace('location.host', host)\
                        .replace('"//res.wx.qq.com/', '"https://res.wx.qq.com/')
    path = '{}/{}.wechat.html'.format(output_path, title)
    open(path, 'w').write(content)
    print(title)

query_text = ''.join(sys.argv[1:])
main(query_text)