python爬取網(wǎng)頁內(nèi)容轉換為PDF文件

更新時間：2020年07月28日 15:32:53 作者：007與狼共舞

這篇文章主要為大家詳細介紹了python爬取網(wǎng)頁內(nèi)容轉換為PDF文件，文中示例代碼介紹的非常詳細，具有一定的參考價值，感興趣的小伙伴們可以參考一下

本文實例為大家分享了python爬取網(wǎng)頁內(nèi)容轉換為PDF的具體代碼，供大家參考，具體內(nèi)容如下

將廖雪峰的學習教程轉換成PDF文件，代碼只適合該網(wǎng)站，如果需要其他網(wǎng)站的教程，可靠需要進行稍微的修改。

# 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內(nèi)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] 
  # 標題 
  title = soup.find('h4').get_text() 

  # 標題加入到正文的最前面，居中顯示 
  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標簽的src相對路徑的改成絕對路徑 
  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 "解析錯誤！"

#----------------------------------------------------------------------
def get_url_list(): 
 """ 
 獲取所有URL目錄列表 
 :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"轉換完成第"+str(i)+'個html' 

 merger = PdfFileMerger() 
 for pdf in pdfs:
  merger.append(open(pdf,'rb'))
  print u"合并完成第"+str(i)+'個pdf'+pdf 

 output = open(u"廖雪峰Python_all.pdf", "wb") 
 merger.write(output) 

 print u"輸出PDF成功！" 

 for html in htmls: 
  os.remove(html) 
  print u"刪除臨時文件"+html 

 for pdf in pdfs: 
  os.remove(pdf) 
  print u"刪除臨時文件"+pdf 

 total_time = time.time() - start 
 print(u"總共耗時：%f 秒" % total_time)

#----------------------------------------------------------------------
def changeDir(dir_name):
 """
 目錄切換
 """
 if not os.path.exists(dir_name):
  os.mkdir(dir_name)

 os.chdir(dir_name)
#----------------------------------------------------------------------
if __name__ == '__main__':
 #存放文件的路徑
 dir_name = '/home/Python/Html' 
 changeDir(dir_name)
 main()

以上就是本文的全部內(nèi)容，希望對大家的學習有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章: