本文實例為大家分享了python爬取網頁內容轉換為PDF的具體代碼，供大家參考，具體內容如下
將廖雪峰的學習教程轉換成PDF文件，代碼只適合該網站，如果需要其他網站的教程，可靠需要進行稍微的修改。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
|
# coding=utf-8 import os import re import time import pdfkit import requests from bs4 import BeautifulSoup from PyPDF2 import PdfFileMergerimport sysreload(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容，希望對大家的學習有所幫助，也希望大家多多支持服務器之家。
原文鏈接：https://blog.csdn.net/manjianchao/article/details/71122815
