python爬取网页内容转换为爬取网页内容转换为PDF文件文件
本文实例为大家分享了python爬取网页内容转换为PDF的具体代码,供大家参考,具体内容如下
将廖雪峰的学习教程转换成PDF文件,代码只适合该网站,如果需要其他网站的教程,可靠需要进行稍微的修改。
# coding=utf-8
import os
import re
import time
import pdfkit
import requests
from bs4 import BeautifulSoup
from PyPDF2 import PdfFileMerger
import sys
reload(sys)
sys.setdefaultencoding('utf8')
html_template = """
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
</head>
<body>
{content}
</body>
</html>
"""
#----------------------------------------------------------------------
def parse_url_to_html(url, name):
"""
解析URL,返回HTML内容
:param url:解析的url
:param name: 保存的html文件名
:return: html
"""
try:
response = requests.get(url)
soup = BeautifulSoup(response.content, 'html.parser')
# 正文
body = soup.find_all(class_="x-wiki-content")[0] # 标题
title = soup.find('h4').get_text()
# 标题加入到正文的最前面,居中显示
center_tag = soup.new_tag("center")
title_tag = soup.new_tag('h1')
title_tag.string = title
center_tag.insert(1, title_tag)
body.insert(1, center_tag)
html = str(body)
# body中的img标签的src相对路径的改成绝对路径
pattern = "(<img .*?src=\")(.*?)(\")"
def func(m):
if not m.group(3).startswith("http"):
rtn = m.group(1) + "http://www.liaoxuefeng.com" + m.group(2) + m.group(3)
return rtn
else:
return m.group(1)+m.group(2)+m.group(3)
html = re.compile(pattern).sub(func, html)
html = html_template.format(content=html)
html = html.encode("utf-8")
with open(name, 'wb') as f:
f.write(html)
return name
评论0