{
  "id": "2004-november-scrape-away",
  "slug": "2004-november-scrape-away",
  "url": "https://dwillis.github.io/uplink/article/2004-november-scrape-away.html",
  "year": 2004,
  "month": "November",
  "monthNum": 11,
  "headline": "Scrape away",
  "kicker": "INSIDE NICAR",
  "author_name": "",
  "author_title": "",
  "affiliation": "IRE and NICAR",
  "summary": "IRE and NICAR have launched the Scraping Project to help journalists efficiently extract data from online public databases by sharing and collaborating on web scraping scripts that can be modified and reused.",
  "keywords": [
    "scraping",
    "data",
    "journalists"
  ],
  "topics": [
    "Investigative Methods",
    "Data & Databases",
    "Journalism & Newsroom"
  ],
  "technologies": [
    "World Wide Web"
  ],
  "full_text": "IRE and NICAR are seeking contributors to the Scraping Project, which was formed to address the concerns of jour- nalists who need to quickly pro- cess public data on the Web. An increasing number of public da- tabases are available online, but they are often stored on multiple pages accessible only by lengthy search strings. This project is an effort to help jour- nalists share scripts that \"scrape\" data from Web sites for use in spreadsheet or database programs. To begin the project, IRE and NICAR are collecting any scraping scripts, explanatory notes and databases, either simple or complex. The Scrap- ing Project will make these scripts available for journalists to modify and use, provided they also share their modified scripts and documentation. For more information about the scraping project see the October- November 2004 issue of Uplink. If you would like to submit a script, contact Jeff Porter at jeff@ire.org.",
  "provenance": {
    "extracted_by": "pre-v2",
    "extracted_at": "",
    "verified": true
  },
  "similar": [
    {
      "slug": "2004-september-october-scraping-away-for-useful-data",
      "score": 0.698
    },
    {
      "slug": "2004-september-october-scaping-for-data-the-perl-way",
      "score": 0.208
    },
    {
      "slug": "2003-novemberdecember-new-service-opens-door-to-most-recent-data",
      "score": 0.103
    },
    {
      "slug": "2000-june-nicar-on-the-web",
      "score": 0.102
    },
    {
      "slug": "1992-september-real-help-for-data-junkies",
      "score": 0.101
    }
  ],
  "html_url": "https://dwillis.github.io/uplink/article/2004-november-scrape-away.html",
  "json_url": "https://dwillis.github.io/uplink/article/2004-november-scrape-away.json"
}