python下载日语语法并保存为pdf

标签：step   路径   www   arp   parse   content   xpl   res   for   

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

__author__ = 'jiangwenwen'

import pdfkit
import requests
from bs4 import BeautifulSoup

# 获取所有的语法列表
response = requests.get("http://www.coelang.tufs.ac.jp/mt/ja/gmod/steplist.html")
soup = BeautifulSoup(response.content, 'html.parser')
grammarList = soup.find_all("li", class_="list")

# 循环语法列表
for grammar in grammarList:
    # 语法标题
    grammarTitle = grammar.a.string.replace('/', '／')
    # 语法链接
    grammarURL = "http://www.coelang.tufs.ac.jp/mt/ja/gmod/contents/explanation/%s.html" % (grammar.a.get('href')[-8:-5])
    # 语法内容
    grammarContent = requests.get(grammarURL).text
    # 语法保存路径
    grammarPath = r'/home/grammar/%s.pdf' % grammarTitle
    # 转换为pdf文件
    pdfkit.from_url(grammarContent, grammarPath)

python下载日语语法并保存为pdf

标签：step   路径   www   arp   parse   content   xpl   res   for   

原文地址：https://www.cnblogs.com/jiangwenwen1/p/11076546.html