@article{cho2006stanford,
  abstract = {We describe the design and performance of WebBase, a tool for Web research. The system includes a highly customizable crawler, a repository for collected Web pages, an indexer for both text and link-related page features, and a high-speed content distribution facility. The distribution module enables researchers world-wide to retrieve pages from WebBase, and stream them across the Internet at high speed. The advantage for the researchers is that they need not all crawl the Web before beginning their research. WebBase has been used by scores of research and teaching organizations world-wide, mostly for investigations into Web topology and linguistic content analysis. After describing the system's architecture, we explain our engineering decisions for each of the WebBase components, and present respective performance measurements.},
  acmid = {1149124},
  address = {New York, NY, USA},
  author = {Cho, Junghoo and Garcia-Molina, Hector and Haveliwala, Taher and Lam, Wang and Paepcke, Andreas and Raghavan, Sriram and Wesley, Gary},
  doi = {10.1145/1149121.1149124},
  interhash = {bebbc072ea2dccf4c2b27abf244c1f08},
  intrahash = {3cd21bf8a87619e0489b8da177c9f0b4},
  issn = {1533-5399},
  issue_date = {May 2006},
  journal = {ACM Transactions on Internet Technology},
  month = may,
  number = 2,
  numpages = {34},
  pages = {153--186},
  publisher = {ACM},
  title = {Stanford WebBase components and applications},
  url = {http://doi.acm.org/10.1145/1149121.1149124},
  volume = 6,
  year = 2006
}