将 JS/CSS/HTML 合并为单个 HTML

Question

我有一个包含 2 个 HTML 文件、6 个 CSS 文件和 11 个 JS 文件的小型本地 Web 应用程序。

1. 如果所有这些文件都是 （正确）复制粘贴到单个 HTML 文件中，例如将 JS 放入 <script> 标记在标题中，并将 CSS 放在 <style> 标记中？

2. 有没有人知道一个工具可以 自动安全地合并 JS、CSS 和 HTML 的集合 文件转换成一个 HTML？

在网上搜索，我只发现可以一次合并或缩小一种类型的文件的工具，但不能创建合并的 HTML 文件（例如AIOM+、HTMLcompressor. 我确实找到了这个名为 Inliner 的应用程序，但它似乎运行在 Node.js 上，我不熟悉并且目前不使用它。

简而言之，我正在寻找一种简单的独立工具，它可以读取 HTML 中的所有链接文件，并通过附加这些文件的内容来重写 HTML。如果这要求太多，那么只需确认手动完成工作会产生工作文件，或者在这样做时要考虑的任何提示。谢谢！

Answer 1

1.

一般来说是的

2.

我不知道合并多个 html 文件，但
Here is a Python script (Github) 用于将 css/js/images 合并到一个 html 文件中。除了 Noam Nol 的回答..

• ...它没有外部依赖项
• ...它还可以正确处理非png图像。

用法： python3 htmlmerger yourfile.html

来自 github 的代码：htmlmerger.py

以下是 Github 上文件的内容。

from html.parser import HTMLParser
import os
import sys
import base64


gHelp = """
Merge JS/CSS/images/HTML into one single file
Version: 1.0

Usage:
  htmlmerger inputfile [optional: outputfile]

"""


def getFileContent (strFilepath):
  content = ""
  with open (strFilepath, "r") as file:
    content = file.read ()
  return content



def getFileContentBytes (strFilepath):
  content = b""
  with open (strFilepath, "rb") as file:
    content = file.read ()
  return content


class HtmlMerger(HTMLParser):
  """
    Call "run(htmlContent, basedir)"  to merge
    script/css/images referenced withing htmlContent
    into one single html file.
  """
  def __init__(self):
    super().__init__()
    self._result = ""
    self._additionalData = ""
    self._baseDir = ""
    self.messages = []



  def _addMessage_fileNotFound(self, file_asInHtmlFile, file_searchpath):
    self.messages.append ("Error: Line " + str (self.getpos ()[0]) +
                        ": Could not find file `" + str (file_asInHtmlFile) +
                        "`; searched in `" + str (file_searchpath) + "`." )



  def _getAttribute (self, attributes, attributeName):
    """Return attribute value or `None`, if not existend"""
    for attr in attributes:
      key = attr[0]
      if (key == attributeName):
        return attr[1]
    return None


  def _getFullFilepath (self, relPath):
    return os.path.join (self._baseDir, relPath)


  def handle_starttag(self, tag, attrs):

    # Style references are within `link` tags. So we have to
    #  convert the whole tag
    if (tag == "link"):
      href = self._getAttribute (attrs, "href")
      if (href):
        hrefFullPath = self._getFullFilepath (href)
        if (not os.path.isfile (hrefFullPath)):
          self._addMessage_fileNotFound (href, hrefFullPath)
          return
        styleContent = getFileContent (hrefFullPath)
        self._result += "<style>" + styleContent + "</style>"
        return

    self._result += "<" + tag + " "

    for attr in attrs:
      key = attr[0]
      value = attr[1]

      # main work: read source content and add it to the file
      if (tag == "script" and key == "src"):
        #self._result += "type='text/javascript'"
        strReferencedFile = self._getFullFilepath (value)
        if (not os.path.isfile (strReferencedFile)):
          self._addMessage_fileNotFound (value, strReferencedFile)
          continue
        referencedContent = getFileContent (strReferencedFile)
        self._additionalData += referencedContent

        # do not process this key
        continue

      if (tag == "img" and key == "src"):
        imgPathRel = value
        imgPathFull = self._getFullFilepath (imgPathRel)
        if (not os.path.isfile (imgPathFull)):
          self._addMessage_fileNotFound (imgPathRel, imgPathFull)
          continue

        imageExtension = os.path.splitext (imgPathRel)[1][1:]
        imageFormat = imageExtension

        # convert image data into browser-undertandable src value
        image_bytes = getFileContentBytes (imgPathFull)
        image_base64 = base64.b64encode (image_bytes)
        src_content = "data:image/{};base64, {}".format(imageFormat,image_base64.decode('ascii'))
        self._result += "src='" + src_content + "'"

        continue



      # choose the right quotes
      if ('"' in value):
        self._result += key + "='" + value + "' "
      else:
        self._result += key + '="' + value + '" '

    self._result +=  ">"

  def _writeAndResetAdditionalData(self):
    self._result += self._additionalData
    self._additionalData = ""

  def handle_endtag(self, tag):
    self._writeAndResetAdditionalData ()
    self._result += "</" + tag + ">"


  def handle_data(self, data):
    self._result += data

  def run(self, content, basedir):
    self._baseDir = basedir
    self.feed (content)
    return self._result



def merge(strInfile, strOutfile):

  if (not os.path.isfile (strInfile)):
    print ("FATAL ERROR: file `" + strInfile + "` could not be accessed.")
    return

  baseDir = os.path.split (os.path.abspath (strInfile))[0]

  #read file
  content = getFileContent (strInfile)

  parser = HtmlMerger()
  content_changed = parser.run (content, baseDir)

  # log errors
  if (len (parser.messages) > 0):
    print ("Problems occured")
    for msg in parser.messages:
      print ("  " + msg)
    print ("")

  # debug:
  if (False):
    print (content_changed)
    exit ()


  # write result
  with open (strOutfile, "w") as file:
    file.write (content_changed)



def main():
  args = sys.argv[1:] # cut away pythonfile
  if (len (args) < 1):
    print (gHelp)
    exit()

  inputFile = args[0]

  # get output file name
  outputFile = ""
  if (True):
    outputFile = os.path.splitext (inputFile)[0] + "_merged.html"

    if (len (args) > 1):
      outputFile = args[1]

    if (os.path.isfile (outputFile)):
      print ("FATAL ERROR: Output file " + outputFile + " does already exist")
      exit ()

  # run the actual merge
  merge (inputFile, outputFile)


main()

Answer 2

我为它写了一个简单的python脚本。

这是我的树：

root-folder
├── index.html
├── build_dist.py
├── js
│   └── somescript.js
├── css
│   ├── styles1.css
│   └── styles2.css
└── dist

我运行脚本：

cd root-folder
python build_dist.py

并且在 dist 文件夹中创建了一个 oneindex.html 文件。
此文件包含 index.html 中使用 link 和 script 标记指定的文件中的所有 js 和 css。
您可以在任何地方使用此文件。

注意：

1. HTML 文件必须是根文件夹中的“index.html”。
2. 它仅适用于单个 HTML 文件。我不知道你想对多个 HTML 文件做什么。

---

build_dist.py 代码：

# build_dist.py

from bs4 import BeautifulSoup
from pathlib import Path
import base64

original_html_text = Path('index.html').read_text(encoding="utf-8")
soup = BeautifulSoup(original_html_text)

# Find link tags. example: <link rel="stylesheet" href="css/somestyle.css">
for tag in soup.find_all('link', href=True):
    if tag.has_attr('href'):
        file_text = Path(tag['href']).read_text(encoding="utf-8")

        # remove the tag from soup
        tag.extract()

        # insert style element
        new_style = soup.new_tag('style')
        new_style.string = file_text
        soup.html.head.append(new_style)


# Find script tags. example: <script src="js/somescript.js"></script>
for tag in soup.find_all('script', src=True):
    if tag.has_attr('src'):
        file_text = Path(tag['src']).read_text()

        # remove the tag from soup
        tag.extract()

        # insert script element
        new_script = soup.new_tag('script')
        new_script.string = file_text
        soup.html.body.append(new_script)

# Find image tags.
for tag in soup.find_all('img', src=True):
    if tag.has_attr('src'):
        file_content = Path(tag['src']).read_bytes()

        # replace filename with base64 of the content of the file
        base64_file_content = base64.b64encode(file_content)
        tag['src'] = "data:image/png;base64, {}".format(base64_file_content.decode('ascii'))

# Save onefile
with open("dist/oneindex.html", "w", encoding="utf-8") as outfile:
    outfile.write(str(soup))

Answer 3

您可以考虑使用webpack。一开始并不容易理解，但这是一个很好的 tutorial 开头。