1. Interactive Wrapper Generation with Minimal User Effort Utku Irmak and Torsten Suel CIS Department Polytechnic University Brooklyn, NY 11201 uirmak@cis.poly.eduuirmak@cis.poly.edu and suel@poly.edusuel@poly.edu

2. Introduction Information on WWW is usually unstructured in nature, and presented via HTML Not appropriate for (certain types of) automatic processing Significant amount of embedded structured data Stock data, product/price data, various statistics, … Expressed through layout, HTML structure Wrapper: a software tool and set of rules for extracting such structured data from web pages Challenge: different sites, variations within sites

3. An Example: Meta Search Engine

4. RankTitleURLSnippet 1Parallel and Distributed Databases www.csse.monash...... Introduction … 2distributed and parallel databases springerlink.com/app... 3Shared Cache – The Future of Parallel Databases csdl2.computer.org…… Shared Cache – The future … 4Distributed and Parallel Databases www.informatik.uni- trier.edu/... … Distributed and Parallel…

5. Introduction Extracting the relevant data embedded in web pages and store in a relational structure for further processing Specialized software programs called wrappers Manual wrappers: e.g., Perl scripts … Due to shortcomings of manually developing wrappers, many tools have been proposed for generating wrappers Semi-automatic (interactive and non-interactive) Fully-automatic

6. An Example: Meta Search Engine

7. Our Goal in this Work Design a complete interactive system for generating wrappers Developed for industrial application Overcome common obstacles such as Missing (multiple) attributes Visual variations Minimize user effort Create robust and reliable wrappers on future pages

8. Related Work Semi-automatic approaches WIEN, SoftMealy, STALKER, Active learning techniques are employed by Muslea et al. Semi-automatic interactive approaches W4F, XWrap, Lixto Fully-automatic approaches IEPAD, RoadRunner, work by Zhai et al.

9. Our Contributions We describe a new system for semi-automatic wrapper generation based on an interactive interface a powerful extraction language ranking of likely candidate sets To implement the interface, we describe a framework based on active learning We propose the use of a category utility function for ranking the tuple sets We perform a detailed experimental evaluation

10. Framework User Training Webpage Verification Set Wrapper Generation System Input: - a training webpage - a number of verification pages

11. Framework User Training Webpage Verification Set Wrapper Generation System (1)User highlights a tuple on training webpage

12. Framework User Training Webpage Verification Set Wrapper Generation System (2) Selected tuple submitted to our system, which generates several wrappers

13. Framework User Training Webpage Verification Set Wrapper Generatio n System ? (3a) System presents user with a candidate tuple set

14. Framework User Training Webpage Verification Set Wrapper Generation System ? ? ? (3b) System presents user with another candidate tuple set

15. Framework User Training Webpage Verification Set Wrapper Generation System ? (3c) System presents user with another candidate tuple set

16. Framework User Training Webpage Verification Set Wrapper Generation System (4) User selects one of the proposed candidate tuple set

17. Framework User Training Webpage Verification Set Wrapper Generation System (5) System refines wrapper and tests it on verification set

18. Framework User Training Webpage Verification Set Wrapper Generation System ! (6) System finds one page where the wrapper disagrees

19. Framework User Training Webpage Verification Set Wrapper Generation System ? ? ? (7a) System presents user with a candidate tuple set on this page in verification set

20. Framework User Training Webpage Verification Set Wrapper Generation System ? ? (7b) System presents user with another candidate tuple set on page in verification set

21. Framework User Training Webpage Verification Set Wrapper Generation System (8) User selects one of the proposed candidate tuple set

22. Framework User Verification Set Wrapper Generation System Wrapper Training Webpage (9) System outputs final wrapper

23. Definition: Wrapper A wrapper is a set of extraction rules that agree on all pages considered thusfar (i.e., that extract exactly the same set of tuples on these pages) The extraction rules within a wrapper may disagree on not yet encountered web pages In this case, a wrapper can be refined by removing some of the extraction rules

24. Summary of Interaction Steps: User highlights a tuple on training page This allows system to generate a number of wrappers that capture different candidate tuple sets System presents candidate tuple sets on the training page to user, in order of plausibility User selects the correct tuple set System tests resulting wrapper on verification set to find any disagreements For any disagreement, user selects the correct set from a ranked list of choices

25. A Real Example: half.ebay.com Extract tuple with attributes: Price, Total Price, Shipping, Seller Only extract those tuples that: Are listed in Like New Items and Whose sellers are awarded a Red Star

26. A Real Example: half.ebay.com

27. Training page:

28. Observations: There can be a lot of unexpected cases and variations on real websites A powerful language is needed to specify extraction rules Simple extraction followed by SQL filtering conditions will often not work The final wrapper may still contain many extraction rules and may disagree on webpages encountered in the future

29. User Effort: (0) Cost of defined table structure: number of attribute, their names, maybe types (1) Cost of highlighting one (or maybe two) tuples on training pages (2) Cost of one or more selections from a ranked list of candidate tuple sets

30. To Implement We Need: (0) User interface based browser extensions (1) Powerful extraction language (2) Algorithms for generating extraction rules and grouping them into wrappers (3) Techniques for ranking wrappers in terms of plausibility (4) Heuristics for throwing away bizarro rules

31. System Architecture Overview

32. Document Representation

33. Extraction Language Overview Based on DOM-tree with auxiliary properties Extraction patterns consists of a sequence of expressions on the path from root to a tuple attribute Each expression consists of conjunctions and disjunctions of predicates If a node at depth i Satisfies its expression: Accept Otherwise: Reject Only children of accepted nodes are checked further for the expression defined at depth i+1

34. Predicates in the Extraction Language Element Nodes tagName tagAttr tagAttrArray elementSiblingPosition tagPstn … Text Nodes textNode textSiblingPosition syntax leftTextNode leftElementNode …

35. The Wrapper Structure

36. Wrapper Generation Algorithm Creating dom_path and LCA objects Creating patterns that extract tuple attributes Creating initial wrappers Generating the tuple validation rules and new wrappers Combining the wrappers Ranking the tuple sets Getting confirmation from the user Testing the wrapper on the verification set

37. Ranking the Tuple Sets We adopt the concept of category utility: Maximize inter-cluster dissimilarity Minimize intra-cluster similarity Dom-Path, specific value, missing attributes, indexing, content specification 1) The weight of attribute A 2) The probability that an item has value v for attribute A, given it belongs to cluster C 3) The probability that an item belongs to cluster C, given it has value v for attribute A S0S0 T

38. Ranking: Discussion Note: we are ranking tuple sets and wrappers A wrapper is more plausible if the tuples is extracted are very similar to each other, and if those tuples are very different from the non-tuples One could also try to rank extraction patterns, say using MDL

39. Experimental Evaluations Number of training tuples required by our system and previous works Results on four previously used data sets from RISE Okra, BigBook, Internet Address Finder, Quote Server

40. Experimental Evaluations We chose ten well- known web sites and collected fifty web pages from each: AltaVista, CNN, Google, Hotjobs, IMDb, YMB (Yahoo! Message Board), MSN Q (MSN Money - Quotes), Weather, Art, and BN (Barnes & Noble)

41. Experimental Evaluation Updating Term Weights (effect of adaptive approach): The effect of pregenerating wrappers for the same extraction scenario on Art and BN websites

42. Summary An approach to interactive wrapper generation that combines Powerful extraction language Techniques for deriving extraction patterns from user input A framework using active learning A ranking technique using a category utility function