python类Markdown()的实例源码

def html_short_summary(self):
        first_line = self.summary.splitlines()[0]
        return markdown(first_line)

def html_summary(self):
        return markdown(self.summary)

def save(self, *args, **kwargs):
        self.body_html = mistune.markdown(self.body_md)
        if not self.slug:
            unique_slugify(self, self.title)
        super(Question, self).save(*args, **kwargs)

def save(self, *args, **kwargs):
        self.body_html = mistune.markdown(self.body_md)
        super(Response, self).save(*args, **kwargs)

def main():
    md = urllib2.urlopen('https://raw.githubusercontent.com/syhw/wer_are_we/master/README.md').read()
    bs = BeautifulSoup(mistune.markdown(md))
    wer_data_file = os.path.abspath(os.path.join(os.path.dirname(__file__),  "../data/wer.py"))
    file_output = "# The file was autogenerated by ../scrapers/wer.py\n\nfrom datetime import date\n\nfrom data.acoustics import speech_recognition, swb_hub_500\nfrom scales import *\n\n"
    wer_metrics = []
    for table, header in zip(bs.findAll('table'), bs.findAll('h3')):
        header = header.getText()
        rows = table.findAll('tr')
        metric_data = get_metrics(header, rows[0].findAll('th')[:-3], file_output)
        metric_names = metric_data[0]
        wer_metrics += metric_names
        table_data = []
        for row in rows:
            if row.findAll('td') == []:
                continue
            measure_data, targets, target_source = add_measures(metric_names, row)
            if not targets:
                table_data += measure_data
            elif not measure_data:
                metric_data = get_metrics(header, rows[0].findAll('th')[:-3], file_output, targets = targets, target_source = target_source)
        file_output = metric_data[1]
        file_output += "".join(sorted(table_data))
    file_output = file_output + "\n\nwer_metrics=[" + ", ".join(wer_metrics) + "]"

    with open(wer_data_file, 'wb') as f:
        f.write(file_output)

def markdown(text):
    return Markup(md.markdown(text,escape=True))

def process_readme(idx, readme_filename, s3_bucket):
    if readme_filename.startswith('npm/'):
        package_name = readme_filename[len('npm/'):]
    if package_name.endswith('/README.json'):
        package_name = package_name[:-len('/README.json')]
    try:
        readme_content = s3_bucket.read_json_file(readme_filename)
    except Exception:
        _logger.warning("[MISSING_DATA] Readme/NPMJS description for package {} does "
                        "not exist in S3.".format(package_name))
        return
    if not readme_content:
        npmjs_description = getNPMdescription(package_name)
        if not npmjs_description:
            _logger.warning("[MISSING_DATA] Readme/NPMJS description for package {} does "
                            "not exist in S3.".format(package_name))
            return
        else:
            readme_content = {
                'type': 'plaintext',
                'content': npmjs_description
            }
    if readme_content['type'] == 'Markdown' or readme_content['type'] == 'plaintext':
        readme_content['content'] = returnContentIfAscii(
            readme_content['content'].replace('\n', ' '))
        if not readme_content['content']:
            _logger.warning("[ENCODING] Ignoring package {} as the readme is not in"
                            " ascii".format(package_name))
            return
        if readme_content['type'] == 'Markdown':
            try:
                readme_content = markdown_preprocess(
                    readme_content['content'])
            except Exception:
                _logger.warning(
                    "[CONTENT] Could not get tags for {}".format(package_name))
                return
        else:
            readme_content = readme_content['content']
        with open(os.path.join(PATH_PREFIX, package_name.replace('/', ':::')), 'w') as of:
            of.write(json.dumps({"id": idx, "text": readme_content}))
        curfilename = of.name
        of.close()
        try:
            tags = run_pipeline(curfilename)
            if tags:
                print(tags)
                tags_dict[package_name] = tags
        except Exception:
            _logger.warning(
                "[CONTENT] Could not get tags for {}".format(package_name))
        os.remove(curfilename)
    else:
        _logger.warning("[FORMAT] Skipping {}, content is not in markdown format"
                        " but in {}.".format(readme_filename, readme_content['type']))

def main(argv):
  if FLAGS.output_dir and FLAGS.output_file:
    sys.stderr.write('Only one of --output_dir or --output_file can be set.')
    sys.exit(1)

  if not FLAGS.output_dir:
    FLAGS.output_dir = DEFAULT_OUTPUT_DIR
  if not FLAGS.output_file:
    FLAGS.output_file = DEFAULT_OUTPUT_FILE

  bzl_files = argv[1:]
  try:
    strip_prefix = common.validate_strip_prefix(FLAGS.strip_prefix, bzl_files)
  except common.InputError as err:
    print(err.message)
    sys.exit(1)

  rulesets = []
  load_sym_extractor = load_extractor.LoadExtractor()
  for bzl_file in bzl_files:
    load_symbols = []
    try:
      load_symbols = load_sym_extractor.extract(bzl_file)
    except load_extractor.LoadExtractorError as e:
      print("ERROR: Error extracting loaded symbols from %s: %s" %
            (bzl_file, str(e)))
      sys.exit(2)

    # TODO(dzc): Make MacroDocExtractor and RuleDocExtractor stateless.
    macro_doc_extractor = macro_extractor.MacroDocExtractor()
    rule_doc_extractor = rule_extractor.RuleDocExtractor()
    macro_doc_extractor.parse_bzl(bzl_file)
    rule_doc_extractor.parse_bzl(bzl_file, load_symbols)
    merged_language = merge_languages(macro_doc_extractor.proto(),
                                      rule_doc_extractor.proto())
    rulesets.append(
        rule.RuleSet(bzl_file, merged_language, macro_doc_extractor.title,
                     macro_doc_extractor.description, strip_prefix,
                     FLAGS.format))
  writer_options = WriterOptions(
      FLAGS.output_dir, FLAGS.output_file, FLAGS.zip, FLAGS.overview,
      FLAGS.overview_filename, FLAGS.link_ext, FLAGS.site_root)
  if FLAGS.format == "markdown":
    markdown_writer = MarkdownWriter(writer_options)
    markdown_writer.write(rulesets)
  elif FLAGS.format == "html":
    html_writer = HtmlWriter(writer_options)
    html_writer.write(rulesets)
  else:
    sys.stderr.write(
        'Invalid output format: %s. Possible values are markdown and html'
        % FLAGS.format)