本文執行個體講述了Python實現抓取HTML網頁並以PDF檔案形式儲存的方法。分享給大家供大家參考，具體如下：
一、前言
今天介紹將HTML網頁抓取下來，然後以PDF儲存，廢話不多說直接進入教程。
二、準備工作
1. PyPDF2的安裝使用（用來合并PDF）：
PyPDF2版本：1.25.1
安裝：
pip install PyPDF2
使用樣本：
from PyPDF2 import PdfFileMergermerger = PdfFileMerger()input1 = open("hql_1_20.pdf", "rb")input2 = open("hql_21_40.pdf", "rb")merger.append(input1)merger.append(input2)# Write to an output PDF documentoutput = open("hql_all.pdf", "wb")merger.write(output)
2. requests、beautifulsoup 是爬蟲兩大神器，reuqests 用於網路請求，beautifusoup 用於操作 html 資料。有了這兩把梭子，幹起活來利索。scrapy 這樣的爬蟲架構我們就不用了，這樣的小程式派上它有點殺雞用牛刀的意思。此外，既然是把 html 檔案轉為 pdf，那麼也要有相應的庫支援， wkhtmltopdf 就是一個非常的工具，它可以用適用於多平台的 html 到 pdf 的轉換，pdfkit 是 wkhtmltopdf 的Python封裝包。首先安裝好下面的依賴包
pip install requestspip install beautifulsoup4pip install pdfkit
3. 安裝 wkhtmltopdf
Windows平台直接在 http://wkhtmltopdf.org/downloads.html 下載穩定版的 wkhtmltopdf 進行安裝，安裝完成之後把該程式的執行路徑加入到系統內容 $PATH 變數中，否則 pdfkit 找不到 wkhtmltopdf 就出現錯誤 “No wkhtmltopdf executable found”。Ubuntu 和 CentOS 可以直接用命令列進行安裝
$ sudo apt-get install wkhtmltopdf # ubuntu$ sudo yum intsall wkhtmltopdf # centos
三、資料準備
1. 擷取每篇文章的url
def get_url_list(): """ 擷取所有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
2. 通過文章url用模板儲存每篇文章的HTML檔案
html模板：
html_template = """<!DOCTYPE html><html lang="en"><head> <meta charset="UTF-8"></head><body>{content}</body></html>"""
進行儲存：
def parse_url_to_html(url, name): """ 解析URL，返回HTML內容 :param url:解析的url :param name: 儲存的html檔案名稱 :return: html """ try: response = requests.get(url) soup = BeautifulSoup(response.content, 'html.parser') # 本文 body = soup.find_all(class_="x-wiki-content")[0] # 標題 title = soup.find('h4').get_text() # 標題加入到本文的最前面，置中顯示 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標籤的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: logging.error("解析錯誤", exc_info=True)
3. 把html轉換成pdf
def save_pdf(htmls, file_name): """ 把所有html檔案儲存到pdf檔案 :param htmls: html檔案清單 :param file_name: pdf檔案名稱 :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)
4. 把轉換好的單個PDF合并為一個PDF
merger = PdfFileMerger()for pdf in pdfs: merger.append(open(pdf,'rb')) print u"合并完成第"+str(i)+'個pdf'+pdf
完整源碼：
# coding=utf-8import osimport reimport timeimport loggingimport pdfkitimport requestsfrom bs4 import BeautifulSoupfrom PyPDF2 import PdfFileMergerhtml_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內容 :param url:解析的url :param name: 儲存的html檔案名稱 :return: html """ try: response = requests.get(url) soup = BeautifulSoup(response.content, 'html.parser') # 本文 body = soup.find_all(class_="x-wiki-content")[0] # 標題 title = soup.find('h4').get_text() # 標題加入到本文的最前面，置中顯示 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標籤的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: logging.error("解析錯誤", exc_info=True)def get_url_list(): """ 擷取所有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 urlsdef save_pdf(htmls, file_name): """ 把所有html檔案儲存到pdf檔案 :param htmls: html檔案清單 :param file_name: pdf檔案名稱 :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"刪除臨時檔案"+html for pdf in pdfs: os.remove(pdf) print u"刪除臨時檔案"+pdf total_time = time.time() - start print(u"總共耗時：%f 秒" % total_time)if __name__ == '__main__': main()
Start building with 50+ products and up to 12 months usage for Elastic Compute Service
1 on 1 presale consultation
24/7 Technical Support 6 Free Tickets per Quarter Faster Response
Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.
A comprehensive suite of global cloud computing services to power your business
Payment Methods We Support
