获取CSDN文章内容并转换为markdown文本的python_python将csdn文章转为markdown

欢迎关注原创视频教程

Python微信订餐小程序课程视频

https://edu.csdn.net/course/detail/36074

Python实战量化交易理财系统

https://edu.csdn.net/course/detail/35475
网上的一个小工具，可以直接获取csdn文章并转换为markdown格式，感觉不错，推荐下 效果图如下：

核心源代码：

from PySide2.QtWidgets import QApplication,QMainWindow,QPushButton,QPlainTextEdit,QMessageBox
import re
import parsel
import tomd
import requests
class CSDN():
  def __init__(self):
    self.windows = QMainWindow()
    self.windows.resize(450, 300)
    self.windows.setWindowTitle("轻松获取csdn文章--by tansty")
    self.setup_ui()
    self.set_connect()
  def set_connect(self):
    #设置建立联系
    self.button.clicked.connect(self.spider_csdn)
  def setup_ui(self):
    #设置ui界面的建立
    self.button = QPushButton(self.windows)
    self.button.resize(100, 100)
    self.button.move(150, 150)
    self.button.setText("获取文章")
    self.text = QPlainTextEdit(self.windows)
    self.text.setPlaceholderText("请输入需要获取文章的链接")
    self.text.resize(450, 100)
  def spider_csdn(self):
    # 目标文章的链接
    title_url=self.text.toPlainText()
    MessageBox = QMessageBox(self.windows)
    if not title_url:
      MessageBox.critical(self.windows, "错误", "请输入网址")
      return
    head={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36 Edg/84.0.522.52"
    }
    html=requests.get(url=title_url,headers=head).text
    page=parsel.Selector(html)
    #创建解释器
    title=page.css(".title-article::text").get()
    res = re.compile("[^\u4e00-\u9fa5^a-z^A-Z^0-9]")
    restr = ''
    res.sub(restr, title)
    content=page.css("article").get()
    content=re.sub("<a.*?a>","",content)
    content = re.sub("<br>", "", content)
    texts=tomd.Tomd(content).markdown
    #转换为markdown 文件
    with open(title+".md",mode="w",encoding="utf-8") as f:
      f.write("#"+title)
      f.write(texts)
      MessageBox.information(self.windows,"正确","获取文章完成")
if __name__ == '__main__':
  app = QApplication()
  csdn=CSDN()
  csdn.windows.show()
  app.exec_()
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

文件打包下载 链接:

https://pan.baidu.com/s/1R6RcrDagwf1vWzmRCBja4w 提取码: ug6n
精简代码

import re
import parsel
import tomd
import requests

def spider_csdn(title_url):
  # 目标文章的链接
  head={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36 Edg/84.0.522.52"
  }
  html=requests.get(url=title_url,headers=head).text
  page=parsel.Selector(html)
  #创建解释器
  title=page.css(".title-article::text").get()
  res = re.compile("[^\u4e00-\u9fa5^a-z^A-Z^0-9]")
  restr = ''
  res.sub(restr, title)
  content=page.css("article").get()
  content=re.sub("<a.*?a>","",content)
  content = re.sub("<br>", "", content)
  texts=tomd.Tomd(content).markdown
  #转换为markdown 文件
  with open(title+".md",mode="w",encoding="utf-8") as f:
    f.write("#"+title)
    f.write(texts)

if __name__ == '__main__':
  spider_csdn('https://blog.csdn.net/biggbang/article/details/121392167')

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