a-extractor/database.json

Article content extraction database

[
  {
    "domain": "abcnews.go.com/",
    "content": "#container .article-body .article-copy",
    "date": {
      "selector": "meta[name=\"Last-Modified\"]",
      "attr": "content"
    },
    "author": {
      "selector": "meta[property=\"article:author\"]",
      "attr": "content"
    }
  },
  {
    "domain": "aeon.co/",
    "content": ".article__body .article__body__content p",
    "date": {
      "selector": ".article__body__content time.published",
      "attr": "datetime"
    },
    "author": "header .article__body__author-name a"
  },
  {
    "domain": "agroinfo.ro/",
    "date": "#news_page .news_date",
    "content": "#news_body"
  },
  {
    "domain": "arenait.net/\\d+/",
    "content": "article.post .entry-content"
  },
  {
    "author": "a[rel=\"author\"] span[itemprop=\"name\"]",
    "date": {
      "selector": "time.date",
      "attr": "datetime"
    },
    "domain": "arstechnica.com/",
    "content": "article div[itemprop=\"articleBody\"]"
  },
  {
    "domain": "articles.latimes.com/\\d+/",
    "content": "#area-center-w-left .mod-articletext"
  },
  {
    "domain": "artsy.net/article/",
    "author": "#article-root .author",
    "date": "#article-root .date",
    "content": "#article-root .article__text-section"
  },
  {
    "domain": "bbc.com/news/",
    "content": "div.story-body .story-body__inner",
    "author": {
      "selector": "meta[property=\"article:author\"]",
      "attr": "content"
    },
    "date": {
      "selector": ".mini-info-list .date",
      "data": "datetime"
    }
  },
  {
    "domain": "beta.theglobeandmail.com/",
    "content": "article.c-article .c-article-body",
    "author": ".c-article-meta a.c-byline",
    "date": ".c-article-meta time.c-timestamp"
  },
  {
    "author": "#text_idea_show span.author",
    "domain": "bigthink.com/",
    "content": "#text_idea_show .article-body"
  },
  {
    "domain": "bossfeed.net/\\d+/",
    "content": "#content .article-content",
    "date": {
      "selector": "time.published",
      "attr": "datetime"
    },
    "author": "span.author a.url"
  },
  {
    "domain": "businessinsider.com/",
    "content": "#content .post-content"
  },
  {
    "domain": "collectivelyconscious.net/",
    "content": "article.post .pf-content",
    "author": "span.author a[rel=\"author\"]",
    "date": "div.post-meta time.post-date"
  },
  {
    "author": "#gkComponent .createdby",
    "domain": "curentul.info/",
    "content": "#gkComponent .articleContent"
  },
  {
    "domain": "dailymail.co.uk/",
    "content": "div[itemprop=\"articleBody\"]"
  },
  {
    "domain": "deepdotweb.com/\\d+/",
    "author": "article.post .post-meta span:first",
    "content": "article.post .entry"
  },
  {
    "date": ".entry-meta time",
    "domain": "digi24.ro/",
    "content": "article div[itemprop=\"articleBody\"]"
  },
  {
    "author": ".entry-author a.author",
    "domain": "earthsky.org/",
    "content": ".content-container .entry-content"
  },
  {
    "domain": "edition.cnn.com/\\d+/",
    "content": "div[itemprop=\"articleBody\"]"
  },
  {
    "author": "div.o-article_meta_bar__avatar a.th-meta",
    "domain": "engadget.com/\\d+/",
    "content": "article div.article-text"
  },
  {
    "domain": "express.co.uk/\\S+",
    "content": "div[data-type=\"article-body\"] section"
  },
  {
    "domain": "farnamstreetblog.com/\\d+/",
    "content": "article .entry-content",
    "date": {
      "selector": "meta[property=\"article:published_time\"]",
      "attr": "content"
    }
  },
  {
    "domain": "fastcompany.com/\\d+/",
    "content": "article.post__article",
    "author": "cite.post__by",
    "date": ".eyebrow__item time"
  },
  {
    "author": ".content-inner span.author",
    "domain": "finesociety.ro/",
    "content": ".content-inner .standard_section",
    "date": ".content-inner div.date"
  },
  {
    "author": "a.article-by",
    "domain": "firstpost.com/",
    "content": ".article div[itemprop=\"articleBody\"]"
  },
  {
    "domain": "foxnews.com/",
    "content": "article div.article-body"
  },
  {
    "domain": "galacticconnection.com/",
    "content": "article.post .post-content"
  },
  {
    "domain": "gandeste.org/",
    "content": "#content .post"
  },
  {
    "date": "#primary .posted-on time",
    "author": "#primary span.author",
    "domain": "gazetadambovitei.ro/",
    "content": "#primary .entry-content"
  },
  {
    "domain": "gnosticwarrior.com/",
    "author": "span.author",
    "content": "article.post .entry-content"
  },
  {
    "date": "#content .posted-on time",
    "domain": "hackread.com/",
    "content": "#content .entry-content"
  },
  {
    "domain": "hbr.org/\\d+/",
    "content": ".article-content .article",
    "author": ".article-header .byline a",
    "date": {
      "selector": "meta[property=\"article:published_time\"]",
      "attr": "content"
    }
  },
  {
    "domain": "hotnews.ro/",
    "author": ".articol_render .autor a",
    "content": "#articleContent"
  },
  {
    "author": "#content a.author",
    "domain": "howtogeek.com/\\d+/",
    "content": "#content .entry-content"
  },
  {
    "domain": "huffingtonpost.com/entry/",
    "content": "article.entry .entry__text"
  },
  {
    "domain": "info.localytics.com/blog/",
    "content": ".single-post__content",
    "author": "strong.author-block__posted-by--large",
    "date": "h5.single-post__date"
  },
  {
    "date": ".td-post-date time",
    "author": ".td-post-author-name a",
    "domain": "infoalert.ro/\\d+/",
    "content": "article .td-post-content"
  },
  {
    "date": "article .time-info time",
    "domain": "irishmirror.ie/",
    "content": "article div[itemprop=\"articleBody\"]"
  },
  {
    "domain": "isgp-studies.com/\\S+",
    "content": "#article_body",
    "author": "#article_author_and_date",
    "date": "#article_author_and_date"
  },
  {
    "domain": "jamesclear.com/",
    "content": ".block-content article.post",
    "author": {
      "selector": "meta[property=\"article:author\"]",
      "attr": "content"
    },
    "date": {
      "selector": "meta[property=\"article:published_time\"]",
      "attr": "content"
    }
  },
  {
    "date": "#main .authors",
    "domain": "jurnalul.ro/",
    "content": "#main .text"
  },
  {
    "domain": "latimes.com/\\S+",
    "content": "article div[itemprop=\"articleBody\"]"
  },
  {
    "domain": "life.ro/",
    "author": "article.details .content-meta>b>a",
    "date": "article.details .content-meta b.text-secondary",
    "content": "article.details p"
  },
  {
    "author": "article.post span.author_name",
    "domain": "mashable.com/\\d+/",
    "content": "article section.article-content"
  },
  {
    "domain": "merckmanuals.com/\\S+",
    "content": "div.body section.body"
  },
  {
    "domain": "money.cnn.com/\\d+/",
    "content": "#storytext"
  },
  {
    "domain": "nautil.us/issue/",
    "content": "article div[itemprop=\"articleBody\"]",
    "author": {
      "selector": "meta[name=\"citation_author\"]",
      "attr": "content"
    },
    "date": {
      "selector": "meta[itemprop=\"datePublished\"]",
      "attr": "content"
    }
  },
  {
    "domain": "nbcnews.com/",
    "content": "article.article_entry div.article-body"
  },
  {
    "domain": "ncbi.nlm.nih.gov/",
    "content": ".abstract .abstr",
    "date": ".abstract .cit",
    "author": ".abstract .auths"
  },
  {
    "author": "#author",
    "date": "#date",
    "domain": "neonnettles.com/",
    "content": "#detailWrapper article section"
  },
  {
    "domain": "news.com.au/",
    "content": "#story",
    "date": "#story-info .datestamp"
  },
  {
    "domain": "newscientist.com/",
    "content": "article.article .article-body",
    "date": "article .published-date"
  },
  {
    "domain": "newyorker.com/",
    "author": {
      "selector": "main article header a[rel=\"author\"]",
      "attr": "title"
    },
    "date": {
      "selector": "main article header time",
      "attr": "title"
    },
    "content": "#articleBody"
  },
  {
    "domain": "nytimes.com/\\d+/",
    "author": {
      "selector": "meta[name=\"author\"]",
      "attr": "content"
    },
    "date": {
      "selector": "meta[property=\"article:published\"]",
      "attr": "content"
    },
    "content": "#story .story-body"
  },
  {
    "domain": "nzherald.co.nz/",
    "content": "#article-content",
    "date": "header figure .publish"
  },
  {
    "domain": "observator.tv/",
    "author": "#article div.author",
    "date": {
      "selector": "meta[name=\"publish-date\"]",
      "attr": "content"
    },
    "content": "#__content"
  },
  {
    "domain": "pri.org/\\S+/\\S+",
    "content": "#main-content article.node.node-story",
    "author": "#main-content .story__meta"
  },
  {
    "domain": "qz.com/\\d+/",
    "author": "article .item-meta .author-name",
    "date": "article .item-meta .timestamp",
    "content": "article div[itemprop=\"articleBody\"]"
  },
  {
    "date": "#main .published",
    "author": "#main span.author",
    "domain": "romaniaa.ro/\\d+/",
    "content": "#main .entry-content"
  },
  {
    "date": ".article__date time",
    "domain": "rt.com/",
    "content": ".article .text"
  },
  {
    "domain": "rts.earth/\\d+/",
    "content": "article.post .entry-content",
    "date": "article.post .post-date"
  },
  {
    "domain": "smh.com.au/",
    "content": "article div[itemprop=\"articleBody\"]",
    "author": ".signature__info h5[rel=\"author\"]"
  },
  {
    "domain": "start-up.ro/",
    "author": ".article-wrapper .article-authors",
    "content": ".article-wrapper .article-text"
  },
  {
    "date": ".staticPageContent .itemDate",
    "domain": "stiri.tvr.ro/",
    "content": ".staticContainer p"
  },
  {
    "domain": "stirileprotv.ro/",
    "content": "#stuck"
  },
  {
    "author": "a[rel=\"author\"]",
    "domain": "techcrunch.com/\\d+/",
    "content": "article .article-entry.text"
  },
  {
    "author": "a[itemtype=\"http://schema.org/Person\"]",
    "domain": "techradar.com/",
    "content": "#article-body"
  },
  {
    "domain": "telegraph.co.uk/",
    "content": "article[itemprop=\"articleBody\"]",
    "date": {
      "selector": "meta[itemprop=\"datePublished\"]",
      "attr": "content"
    },
    "author": {
      "selector": "meta[name=\"DCSext.author\"]",
      "attr": "content"
    }
  },
  {
    "domain": "theatlantic.com/magazine/",
    "content": "#article div[itemprop=\"articleBody\"] section",
    "date": {
      "selector": "meta[itemprop=\"datePublished\"]",
      "attr": "content"
    },
    "author": {
      "selector": "meta[name=\"author\"]",
      "attr": "content"
    }
  },
  {
    "domain": "theguardian.com/",
    "content": "article div[itemprop=\"articleBody\"]",
    "date": {
      "selector": "meta[property=\"article:published_time\"]",
      "attr": "content"
    },
    "author": {
      "selector": "meta[name=\"author\"]",
      "attr": "content"
    }
  },
  {
    "date": "article .entry-meta-date a",
    "domain": "theliberal.ie/",
    "content": "article .entry-content"
  },
  {
    "author": "article.post a.post-authorName",
    "domain": "thenextweb.com/",
    "content": "article .post-body"
  },
  {
    "domain": "theverge.com/\\d+/",
    "content": ".entry-content",
    "date": "time.c-byline__item",
    "author": ".c-byline__item a"
  },
  {
    "domain": "thrillist.com/",
    "author": "#content a[itemprop=\"author\"]",
    "content": "#content div[itemprop=\"articleBody\"]"
  },
  {
    "date": "article .entry-meta-item time",
    "domain": "torrentfreak.com/",
    "content": "article .entry-content"
  },
  {
    "domain": "usatoday.com/",
    "content": "article.story div[itemprop=\"articleBody\"] p",
    "author": ".asset-metabar .asset-metabar-author",
    "date": ".asset-metabar .asset-metabar-time"
  },
  {
    "domain": "usnews.com/news/",
    "content": "#ad-in-text-target"
  },
  {
    "domain": "vox.com/",
    "author": {
      "selector": "meta[property=\"author\"]",
      "attr": "content"
    },
    "date": {
      "selector": "meta[property=\"article:published_time\"]",
      "attr": "content"
    },
    "content": "section.l-main-content .c-entry-content"
  },
  {
    "date": "article.post .post-box-meta-single",
    "domain": "wakingtimes.com/\\d+/",
    "content": "article.post .inner-post-entry"
  },
  {
    "domain": "wall-street.ro/",
    "author": ".common-padder a.editor span",
    "content": ".common-padder .article-content"
  },
  {
    "domain": "washingtonpost.com/news/",
    "content": "#pb-root div[itemprop=\"articleBody\"]"
  },
  {
    "author": ".content-container .author-details",
    "date": ".content-container .article-published",
    "domain": "weforum.org/",
    "content": ".content-container .article-body"
  },
  {
    "domain": "wsj.com/(?:articles|experts)/",
    "content": "#article_sector .wsj-snippet-body",
    "date": "#article_sector time.timestamp"
  },
  {
    "domain": "yahoo.com/news/",
    "content": "article[itemprop=\"articleBody\"]"
  },
  {
    "domain": "ziare.com/",
    "content": "#content_font_resizable"
  }
]