Python ZIPFileHandler.hasFile方法代码示例

# 需要导入模块: from MaKaC.common.contribPacker import ZIPFileHandler [as 别名]
# 或者: from MaKaC.common.contribPacker.ZIPFileHandler import hasFile [as 别名]

#.........这里部分代码省略.........
        config = Config.getInstance()
        soup = BeautifulSoup(html)
        images = set(_fix_url_path(x['src']) for x in soup.select('img[src]'))
        scripts = set(_fix_url_path(x['src']) for x in soup.select('script[src]'))
        styles = set(_fix_url_path(x['href']) for x in soup.select('link[rel="stylesheet"]'))
        for path in itertools.chain(images, scripts, styles):
            src_path = re.sub(r'#.*$', '', os.path.join(config.getHtdocsDir(), path))
            dst_path = os.path.join(self._staticPath, path)
            if path in styles:
                self._css_files.add(path)
            if not os.path.isfile(src_path):
                self._failed_paths.add(path)
            elif path not in styles:
                self._addFileFromSrc(dst_path, src_path)
        for image in soup.select('img[src]'):
            image['src'] = os.path.join('static', _fix_url_path(image['src']))
        for script in soup.select('script[src]'):
            script['src'] = os.path.join('static', _fix_url_path(script['src']))
        for style in soup.select('link[rel="stylesheet"]'):
            style['href'] = os.path.join('static', _fix_url_path(style['href']))
        return str(soup)

    def _get_failed_paths(self):
        """Downloads files that were not available in the fielystem via HTTP.
        This is the only clean way to deal with static files from plugins since otherwise
        we would have to emulate RHHtdocs.
        """
        cfg = Config.getInstance()
        # If we have the embedded webserver prefer its base url since the iptables hack does
        # not work for connections from the same machine
        base_url = cfg.getBaseURL()
        for path in self._failed_paths:
            dst_path = os.path.join(self._staticPath, path)
            if not self._fileHandler.hasFile(dst_path):
                response = requests.get(os.path.join(base_url, path), verify=False)
                self._downloaded_files[dst_path] = response.content
                self._fileHandler.addNewFile(dst_path, response.content)

    def _get_css_refs(self):
        """Adds files referenced in stylesheets and rewrite the URLs inside those stylesheets"""
        config = Config.getInstance()
        for path in self._css_files:
            src_path = os.path.join(config.getHtdocsDir(), path)
            dst_path = os.path.join(self._staticPath, path)
            if dst_path in self._downloaded_files and not os.path.exists(src_path):
                css = self._downloaded_files[dst_path]
            else:
                with open(src_path, 'rb') as f:
                    css = f.read()
            # Extract all paths inside url()
            urls = set(m.group('url') for m in RE_CSS_URL.finditer(css) if m.group('url')[0] != '#')
            for url in urls:
                orig_url = url
                url = _remove_qs(url)  # get rid of cache busters
                if url[0] == '/':
                    # make it relative and resolve '..' elements
                    url = os.path.normpath(url[1:])
                    # anything else is straightforward: the url is now relative to the htdocs folder
                    ref_src_path = os.path.join(config.getHtdocsDir(), url)
                    ref_dst_path = os.path.join(self._staticPath, url)
                    # the new url is relative to the css location
                    static_url = os.path.relpath(url, os.path.dirname(path))
                else:
                    # make the relative path absolute (note: it's most likely NOT relative to htdocs!)
                    css_abs_path = os.path.join(config.getHtdocsDir(), path)
                    # now we can combine the relative url with that path to get the proper paths of the resource

# 需要导入模块: from MaKaC.common.contribPacker import ZIPFileHandler [as 别名]
# 或者: from MaKaC.common.contribPacker.ZIPFileHandler import hasFile [as 别名]

#.........这里部分代码省略.........
        return self._outputFile

    def _get_static_files(self, html):
        config = Config.getInstance()
        soup = BeautifulSoup(html)
        scripts = set(_fix_url_path(x["src"]) for x in soup.select("script[src]"))
        styles = set(_fix_url_path(x["href"]) for x in soup.select('link[rel="stylesheet"]'))
        for path in itertools.chain(scripts, styles):
            src_path = os.path.join(config.getHtdocsDir(), path)
            dst_path = os.path.join(self._staticPath, path)
            if path in styles:
                self._css_files.add(path)
            if not os.path.isfile(src_path):
                self._failed_paths.add(path)
            elif path not in styles:
                self._addFileFromSrc(dst_path, src_path)
        for script in soup.select("script[src]"):
            script["src"] = os.path.join("static", _fix_url_path(script["src"]))
        for style in soup.select('link[rel="stylesheet"]'):
            style["href"] = os.path.join("static", _fix_url_path(style["href"]))
        return str(soup)

    def _get_failed_paths(self):
        """Downloads files that were not available in the fielystem via HTTP.
        This is the only clean way to deal with static files from plugins since otherwise
        we would have to emulate RHHtdocs.
        """
        cfg = Config.getInstance()
        # If we have the embedded webserver prefer its base url since the iptables hack does
        # not work for connections from the same machine
        base_url = cfg.getEmbeddedWebserverBaseURL() or cfg.getBaseURL()
        for path in self._failed_paths:
            dst_path = os.path.join(self._staticPath, path)
            if not self._fileHandler.hasFile(dst_path):
                response = requests.get(os.path.join(base_url, path), verify=False)
                self._downloaded_files[dst_path] = response.content
                self._fileHandler.addNewFile(dst_path, response.content)

    def _get_css_refs(self):
        """Adds files referenced in stylesheets and rewrite the URLs inside those stylesheets"""
        config = Config.getInstance()
        for path in self._css_files:
            src_path = os.path.join(config.getHtdocsDir(), path)
            dst_path = os.path.join(self._staticPath, path)
            if dst_path in self._downloaded_files and not os.path.exists(src_path):
                css = self._downloaded_files[dst_path]
            else:
                with open(src_path, "rb") as f:
                    css = f.read()
            # Extract all paths inside url()
            urls = set(m.group("url") for m in RE_CSS_URL.finditer(css) if m.group("url")[0] != "#")
            for url in urls:
                orig_url = url
                url = _remove_qs(url)  # get rid of cache busters
                if url[0] == "/":
                    # make it relative and resolve '..' elements
                    url = os.path.normpath(url[1:])
                    # anything else is straightforward: the url is now relative to the htdocs folder
                    ref_src_path = os.path.join(config.getHtdocsDir(), url)
                    ref_dst_path = os.path.join(self._staticPath, url)
                    # the new url is relative to the css location
                    static_url = os.path.relpath(url, os.path.dirname(path))
                else:
                    # make the relative path absolute (note: it's most likely NOT relative to htdocs!)
                    css_abs_path = os.path.join(config.getHtdocsDir(), path)
                    # now we can combine the relative url with that path to get the proper paths of the resource