【python 爬虫】博客文章转 Markdown（支持 LaTeX 公式）_python爬虫将文章保存为markdown

博客文章爬虫

以某乎文章 https://zhuanlan.zhihu.com/p/112277874 为例子，爬取结果：

程序如下：

import os
import sys
import getopt
import requests
import random
import re
import html2text
from bs4 import BeautifulSoup

useragents = [
        'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0',
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    ]


def safe_file_name(file_name):
    return re.sub(r'[\|/|:|*|?|"|<|>|\|]', "", file_name)

def jinashu(url):
    ## 浏览器头部
    headers = {
        'Host': 'www.jianshu.com',
        'Referer': 'https://www.jianshu.com/',
        'User-Agent': random.choice(useragents)
    }
    ## 获取网页主体
    html = requests.get(url,headers=headers).text

    ## bs4
    soup = BeautifulSoup(html,"lxml")
    title = soup.find_all("title")[0].get_text()
    article = str(soup.find_all("div",class_="show-content")[0])

    ## 替图片的src加上https://方便访问
    article = re.sub('(src=")|(data-original-src=")','src="https:',article)

    ## 写入文件
    pwd = os.getcwd() # 获取当前的文件路径
    dirpath = pwd + '/jianshu/'
    write2md(dirpath,title,article)
    
    
def csdn(url):
    headers = {
        'Host': 'blog.csdn.net',
        'Referer': 'http://blog.csdn.net/',
        'User-Agent': random.choice(useragents)
    }
    ## 获取网页主体
    html = requests.get(url,headers=headers).text
    
    ## bs4
    soup = BeautifulSoup(html,'lxml')
    title = soup.find_all('title')[0].get_text()
    article = str(soup.find_all('article')[0])

    ## 写入文件
    pwd = os.getcwd() # 获取当前的文件路径
    dirpath = pwd + '/CSDN/'

    article = csdnEq2Tex(article)
    print(article)

    write2md(dirpath,title,article)


def csdnEq2Tex(content):
    esc = 0
    while esc != -1:
        if content.find('<span class="MathJax_Preview"') != -1:
            start = content.find('<span class="MathJax_Preview"')
            end = content.index('<script id="MathJax-Element', start)
            content = content.replace(content[start:end], '')
            
            start = content.index('<script id="MathJax-Element', start)
            mid = content.index('>', start)
            end = content.find('</script>')

            print(ord(content[start-1]), ord(content[end+10]))

            if content[start:end+9].find("mode=display") != -1:
                content = content.replace(content[start:end+9], '<p>$$</p>'+content[mid+1:end]+'<p>$$</p>')
            else:
                content = content.replace(content[start:end+9], ' $'+content[mid+1:end]+'$ ')

        else:
            esc = -1

    content = content.replace("\n", '')
    content = content.replace('<br/>', '<p></p>')
    return content

def zhihuEq2Tex(content):
    content = content.replace('\\\\', '\\')
    content = content.replace('\\(', '(')
    content = content.replace('\\)', ')')
    content = content.replace('\\[', '[')
    content = content.replace('\\]', ']')
    # print(content)

    pos = 0 
    while pos < content.rfind('!['):
        start = content.index('![', pos)
        mid =  content.index('](', pos)
        end =  content.index(')', mid)

        string = content[start+2:mid]
        string = string.replace('\n', ' ')


        if len(string) != 0:
            # print(len(string))
            if string[-1] == '\\':
                string = '$$\n' + string[:-1] + '\n$$'
            else:
                string = '$\n' + string + '\n$'

            content = content[:start] + string + content[end+1:]


            pos = start + len(string)
        else:

            pos = end 
        
        # print(string)

    return content
   

def zhihu(url):
    headers = {
        'Host': 'zhuanlan.zhihu.com',
        'Referer': 'https://www.zhihu.com/',
        'User-Agent': random.choice(useragents)
    }
    html = requests.get(url,headers=headers).text
    
    ## bs4
    soup = BeautifulSoup(html,'lxml')
    title = soup.find_all('title')[0].get_text()
    article = str(soup.find_all('div',class_='Post-RichText')[0])

    

    ## 写入文件
    pwd = os.getcwd() # 获取当前的文件路径
    dirpath = pwd + '/ZhiHu/'
    write2md(dirpath,title,article)
    

def segmentfault(url):
    headers = {
        # 'Host': 'https://segmentfault.com',
        'Referer': 'https://segmentfault.com/',
        'User-Agent': random.choice(useragents)
    }
    html = requests.get(url,headers=headers).text
    
    ## bs4
    soup = BeautifulSoup(html,'lxml')
    title = soup.find('title').text # 获取标题
    article = str(soup.find(class_='article__content'))

    ## 写入文件
    pwd = os.getcwd() # 获取当前的文件路径
    dirpath = pwd + '/segmentfault/'
    write2md(dirpath,title,article)
    

def juejin(url):
    ## 首先获取文章的id
    postId = url.split('/')[-1]
    ## 目标url
    tar_url = "https://post-storage-api-ms.juejin.im/v1/getDetailData"
    ## 用来获取标题
    data1 = {
        "src":"web",
        "type":"entry",
        "postId":postId
    }
    ## 用来获取文章主体
    data2 = {
        "src":"web",
        "type":"entryView",
        "postId":postId
    }
    res = requests.get(url=tar_url,params=data1)
    res.encoding = "utf-8"
    res = res.json()
    title = res["d"]["title"]
    res = requests.get(url=tar_url,params=data2)
    res.encoding = "utf-8"
    res = res.json()
    article = res["d"]["transcodeContent"]
    ## 写入文件
    pwd = os.getcwd() # 获取当前的文件路径
    dirpath = pwd + '/juejin/'
    write2md(dirpath,title,article)
 
def doelse(url):
    headers = {
        'User-Agent': random.choice(useragents)
    }
    res = requests.get(url=url ,headers=headers) # 获取整个html页面

    h = html2text.HTML2Text()
    h.ignore_links = False
    soup = BeautifulSoup(res.text,'lxml')
    title = soup.title.text # 获取标题
    html = str(soup.body)
    article = h.handle(html)

    pwd = os.getcwd() # 获取当前文件的路径
    dirpath = pwd + '/Else/'
    if not os.path.exists(dirpath):# 判断目录是否存在，不存在则创建新的目录
        os.makedirs(dirpath)
    ## 写入文件
    pwd = os.getcwd() # 获取当前的文件路径
    dirpath = pwd + '/ELSE/'
    write2md(dirpath,title,article)
    

"""
传入文件路径，title，article
"""
def write2md(dirpath,title,article):
    ## 创建转换器
    h2md = html2text.HTML2Text()
    h2md.ignore_links = False
    ## 转换文档
    article = h2md.handle(article)
    article = zhihuEq2Tex(article)
    title  = safe_file_name(title)
    ## 写入文件
    if not os.path.exists(dirpath):# 判断目录是否存在，不存在则创建新的目录
        os.makedirs(dirpath)
    # 创建md文件
    with open(dirpath+title+'.md','w',encoding="utf8") as f:
        lines = article.splitlines()
        for line in lines:
            if line.endswith('-'):
                f.write(line)
            else:
                f.write(line+"\n")
    print(title+"下载完成....")



def main(argv):
    try:
        opts,args = getopt.getopt(argv,"hu:",["url"])
    except getopt.GetoptError:
        print("python html2md.py -u <url>")
    for opt,arg in opts:
        if opt == "-h":
            print("python html2md.py -u <url>")
            sys.exit(2)
        elif opt in ("-u", "-url"):
            print()
            checkSite(arg)
        else:
            print("python html2md.py -u <url>")

## 检查网站，使用哪个下载器
def checkSite(url):
    if url.find('csdn') != -1:
        csdn(url)
    elif url.find('jianshu') != -1:
        jinashu(url)
    elif url.find('zhihu') != -1:
        zhihu(url)
    elif url.find('segmentfault') != -1:
        segmentfault(url)
    elif url.find('juejin') != -1:
        juejin(url)
    else:
        doelse(url)
    
    

if __name__ == "__main__":
    # main(sys.argv[1:])
    checkSite('https://blog.csdn.net/variablex/article/details/109820684')
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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285