parse()

in Readability.js [2731:2789]

• 42 lines of code
• 9 McCabe index (conditional complexity)

  parse() {
    // Avoid parsing too large documents, as per configuration option
    if (this._maxElemsToParse > 0) {
      var numTags = this._doc.getElementsByTagName("*").length;
      if (numTags > this._maxElemsToParse) {
        throw new Error(
          "Aborting parsing document; " + numTags + " elements found"
        );
      }
    }

    // Unwrap image from noscript
    this._unwrapNoscriptImages(this._doc);

    // Extract JSON-LD metadata before removing scripts
    var jsonLd = this._disableJSONLD ? {} : this._getJSONLD(this._doc);

    // Remove script tags from the document.
    this._removeScripts(this._doc);

    this._prepDocument();

    var metadata = this._getArticleMetadata(jsonLd);
    this._metadata = metadata;
    this._articleTitle = metadata.title;

    var articleContent = this._grabArticle();
    if (!articleContent) {
      return null;
    }

    this.log("Grabbed: " + articleContent.innerHTML);

    this._postProcessContent(articleContent);

    // If we haven't found an excerpt in the article's metadata, use the article's
    // first paragraph as the excerpt. This is used for displaying a preview of
    // the article's content.
    if (!metadata.excerpt) {
      var paragraphs = articleContent.getElementsByTagName("p");
      if (paragraphs.length) {
        metadata.excerpt = paragraphs[0].textContent.trim();
      }
    }

    var textContent = articleContent.textContent;
    return {
      title: this._articleTitle,
      byline: metadata.byline || this._articleByline,
      dir: this._articleDir,
      lang: this._articleLang,
      content: this._serializer(articleContent),
      textContent,
      length: textContent.length,
      excerpt: metadata.excerpt,
      siteName: metadata.siteName || this._articleSiteName,
      publishedTime: metadata.publishedTime,
    };
  },