Created
June 11, 2009 14:23
-
-
Save daniello/127916 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
-module(google_scrapper). | |
-compile(export_all). | |
-define(GOOGLE_URL, "http://www.google.co.uk/search?hl=en&btnG=Search&meta=&q="). | |
start() -> inets:start(). | |
fetch_google_results(Q) -> | |
% In case of redirect lets erlang take care of this for us | |
HTTPOptions = [{autoredirect, true}], | |
% We want binary as a result | |
Options = [{body_format, binary}], | |
Headers = [ | |
% Let's be Firefox ;) | |
{"User-Agent", "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.0.10) Gecko/2009042315 Firefox/3.0.10"}, | |
{"Accept" , "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"}, | |
% I want the result be UTF-8 encoded | |
{"Accept-Charset", "utf-8;q=0.7,*;q=0.7"} | |
], | |
Request = {?GOOGLE_URL++url_encoder:encode(Q), Headers}, | |
case http:request(get, Request, HTTPOptions, Options) of | |
{ok, {{"HTTP/1.1",200,"OK"}, _, Body}} -> Body; | |
{error,Error} -> {error,Error} | |
end. | |
parse(B, RE, Fun) -> | |
case re:run(B, RE, [global, caseless, unicode, dotall, multiline, {capture, all, binary}]) of | |
{match, Matches} -> | |
lists:map( | |
fun(Match) -> Fun(Match) end, | |
Matches); | |
nomatch -> [] | |
end. | |
parse_google_results(B) -> | |
RE = "<\\!--m-->(.*?)<\\!--n-->", | |
parse(B, RE, fun parse_google_result/1). | |
parse_google_result(GResult) -> | |
RE = "<li class=g.*?<h3.*?<a href=\"(.*?)\".*?>(.*?)</a>", | |
Fun = fun([_,Href,Name]) -> | |
{Href,Name} | |
end, | |
parse(GResult, RE, Fun). | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment