如何使用python更改html文档的css属性？

我有一个包含许多HTML文档的目录。其中大多数包含代码块

.org链接{
/*组织链接*/
颜色：#b58900；
字体大小：粗体；
文字装饰：下划线；
}

在

标记内。我想写一个脚本，删除行

文本装饰：下划线

并将每个文件中的此块的颜色更改为

#2aa198

---

使用python可以实现这一点吗？

您可以使用正则表达式进行必要的替换，如下所示：

import re

test = """
      .org-link {
        /* org-link */
        color: #b58900;
        font-weight: bold;
        text-decoration: underline;
      }
"""

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

print re.sub(r'(org-link\s+\{.*\})', fix, test, flags=re.S)

  .org-link {
    /* org-link */
    color:#777;
    font-weight: bold;
  }

import re
import glob

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

for html_file in glob.glob('*.html'):
    print html_file
    with open(html_file) as f_input:
        html = re.sub(r'(org-link\s+\{.*\})', fix, f_input.read(), flags=re.S)

    with open(html_file, 'w') as f_output:
        f_output.write(html)

这将把案文转换如下：

import re

test = """
      .org-link {
        /* org-link */
        color: #b58900;
        font-weight: bold;
        text-decoration: underline;
      }
"""

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

print re.sub(r'(org-link\s+\{.*\})', fix, test, flags=re.S)

  .org-link {
    /* org-link */
    color:#777;
    font-weight: bold;
  }

import re
import glob

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

for html_file in glob.glob('*.html'):
    print html_file
    with open(html_file) as f_input:
        html = re.sub(r'(org-link\s+\{.*\})', fix, f_input.read(), flags=re.S)

    with open(html_file, 'w') as f_output:
        f_output.write(html)

它首先识别合适的

组织链接

块，然后首先替换颜色，然后删除任何

文本装饰

条目

然后可以对脚本进行扩展，以便对给定文件夹中的所有HTML文件执行此操作，如下所示：

import re

test = """
      .org-link {
        /* org-link */
        color: #b58900;
        font-weight: bold;
        text-decoration: underline;
      }
"""

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

print re.sub(r'(org-link\s+\{.*\})', fix, test, flags=re.S)

  .org-link {
    /* org-link */
    color:#777;
    font-weight: bold;
  }

import re
import glob

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

for html_file in glob.glob('*.html'):
    print html_file
    with open(html_file) as f_input:
        html = re.sub(r'(org-link\s+\{.*\})', fix, f_input.read(), flags=re.S)

    with open(html_file, 'w') as f_output:
        f_output.write(html)

---

使用Python 2.7.9进行测试，您可以使用正则表达式进行必要的替换，如下所示：

import re

test = """
      .org-link {
        /* org-link */
        color: #b58900;
        font-weight: bold;
        text-decoration: underline;
      }
"""

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

print re.sub(r'(org-link\s+\{.*\})', fix, test, flags=re.S)

  .org-link {
    /* org-link */
    color:#777;
    font-weight: bold;
  }

import re
import glob

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

for html_file in glob.glob('*.html'):
    print html_file
    with open(html_file) as f_input:
        html = re.sub(r'(org-link\s+\{.*\})', fix, f_input.read(), flags=re.S)

    with open(html_file, 'w') as f_output:
        f_output.write(html)

这将把案文转换如下：

import re

test = """
      .org-link {
        /* org-link */
        color: #b58900;
        font-weight: bold;
        text-decoration: underline;
      }
"""

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

print re.sub(r'(org-link\s+\{.*\})', fix, test, flags=re.S)

  .org-link {
    /* org-link */
    color:#777;
    font-weight: bold;
  }

import re
import glob

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

for html_file in glob.glob('*.html'):
    print html_file
    with open(html_file) as f_input:
        html = re.sub(r'(org-link\s+\{.*\})', fix, f_input.read(), flags=re.S)

    with open(html_file, 'w') as f_output:
        f_output.write(html)

它首先识别合适的

组织链接

块，然后首先替换颜色，然后删除任何

文本装饰

条目

然后可以对脚本进行扩展，以便对给定文件夹中的所有HTML文件执行此操作，如下所示：

import re

test = """
      .org-link {
        /* org-link */
        color: #b58900;
        font-weight: bold;
        text-decoration: underline;
      }
"""

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

print re.sub(r'(org-link\s+\{.*\})', fix, test, flags=re.S)

  .org-link {
    /* org-link */
    color:#777;
    font-weight: bold;
  }

import re
import glob

def fix(org_link):
    new_color = re.sub(r'(.*?color\s*?:\s*?)(.*?)(;)', r'\1#777\3', org_link.group(0), flags=re.S)
    return re.sub(r'(.*?)(\s+?text-decoration: underline;)(.*?)', r'\1\3', new_color, flags=re.S)

for html_file in glob.glob('*.html'):
    print html_file
    with open(html_file) as f_input:
        html = re.sub(r'(org-link\s+\{.*\})', fix, f_input.read(), flags=re.S)

    with open(html_file, 'w') as f_output:
        f_output.write(html)

---

使用Python 2.7.9进行测试

文件中是否只有一个

文本装饰

css属性？其他块中是否有多个。可能重复文件中是否只有一个

文本装饰

css属性？其他块中是否有多个。可能重复