python爬取网页内容转换为PDF文件
作者：007与狼共舞 时间：2023-04-29 10:53:12
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
except Exception as e:
print "解析错误！"
#----------------------------------------------------------------------
def get_url_list():
"""
获取所有URL目录列表
:return:
"""
response = requests.get("http://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000")
soup = BeautifulSoup(response.content, "html.parser")
menu_tag = soup.find_all(class_="uk-nav uk-nav-side")[1]
urls = []
for li in menu_tag.find_all("li"):
url = "http://www.liaoxuefeng.com" + li.a.get('href')
urls.append(url)
return urls
#----------------------------------------------------------------------
def save_pdf(htmls, file_name):
"""
把所有html文件保存到pdf文件
:param htmls: html文件列表
:param file_name: pdf文件名
:return:
"""
options = {
'page-size': 'Letter',
'margin-top': '0.75in',
'margin-right': '0.75in',
'margin-bottom': '0.75in',
'margin-left': '0.75in',
'encoding': "UTF-8",
'custom-header': [
('Accept-Encoding', 'gzip')
],
'cookie': [
('cookie-name1', 'cookie-value1'),
('cookie-name2', 'cookie-value2'),
],
'outline-depth': 10,
}
pdfkit.from_file(htmls, file_name, options=options)
#----------------------------------------------------------------------
def main():
start = time.time()
file_name = u"liaoxuefeng_Python3_tutorial"
urls = get_url_list()
for index, url in enumerate(urls):
parse_url_to_html(url, str(index) + ".html")
htmls =[]
pdfs =[]
for i in range(0,124):
htmls.append(str(i)+'.html')
pdfs.append(file_name+str(i)+'.pdf')
save_pdf(str(i)+'.html', file_name+str(i)+'.pdf')
print u"转换完成第"+str(i)+'个html'
merger = PdfFileMerger()
for pdf in pdfs:
merger.append(open(pdf,'rb'))
print u"合并完成第"+str(i)+'个pdf'+pdf
output = open(u"廖雪峰Python_all.pdf", "wb")
merger.write(output)
print u"输出PDF成功！"
for html in htmls:
os.remove(html)
print u"删除临时文件"+html
for pdf in pdfs:
os.remove(pdf)
print u"删除临时文件"+pdf
total_time = time.time() - start
print(u"总共耗时：％f 秒" ％ total_time)
#----------------------------------------------------------------------
def changeDir(dir_name):
"""
目录切换
"""
if not os.path.exists(dir_name):
os.mkdir(dir_name)
os.chdir(dir_name)
#----------------------------------------------------------------------
if __name__ == '__main__':
#存放文件的路径
dir_name = '/home/Python/Html'
changeDir(dir_name)
main()
来源：https://blog.csdn.net/manjianchao/article/details/71122815
标签：python,爬取,pdf
0
投稿猜你喜欢
Python还能这么玩之用Python修改了班花的开机密码
2023-11-23 17:38:40
windows下MySQL5.6版本安装及配置过程附有截图和详细说明
2024-01-13 18:58:56
MySql索引原理与操作
2024-01-28 22:27:31
Python里的dict和set的背后小秘密
2023-11-20 01:01:11
CSS盒模型
2009-06-09 14:23:00
Python 使用指定的网卡发送HTTP请求的实例
2022-07-05 05:30:00
JavaScript中的toDateString()方法使用详解
2024-05-13 10:37:51
JS弹出可拖拽可关闭的div层完整实例
2024-04-19 09:50:56
golang 实现并发求和
2024-02-02 07:15:58
PHP实战之投票系统的实现
2023-10-24 10:40:39
解决MySQL 5.7.9版本sql_mode=only_full_group_by问题
2024-01-26 15:02:22
Django框架获取form表单数据方式总结
2022-08-21 14:24:29
Python from import导包ModuleNotFoundError No module named找不到模块问题解决
2023-07-27 20:06:53
RC4文件加密的python实现方法
2023-12-21 20:25:28
MySQL Community Server 8.0.11安装配置方法图文教程
2024-01-26 06:02:45
离线状态下在jupyter notebook中使用plotly实例
2022-04-19 18:05:59
详解Vue2的diff算法
2024-04-28 09:30:48
Python的三个重要函数详解
2022-05-19 04:58:45
Form表单及django的form表单的补充
2023-07-21 09:40:04
opencv实现回形遍历像素算法
2021-12-26 01:49:30
