Created
August 15, 2017 13:14
-
-
Save LitvinenkoD89/60edfbedfc8852cd22baeca337728755 to your computer and use it in GitHub Desktop.
ucaoa_console_test
This file contains hidden or 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
url = "http://www.ucaoa.org/searchserver/people.aspx?id=AA614225-2260-4578-9513-18089A0F8951&cdbid=&canconnect=0&canmessage=0&map=False&toggle=True&hhSearchTerms=" | |
t = Typhoeus.get url | |
page = Nokogiri::HTML t.body | |
links = [] | |
pagination = (2..10).to_a | |
pagination.each do |page_num| | |
body = page.at('#SearchResultsForm').search('input').inject({}){|acc,c| acc[c.attr('name')] = c.attr('value'); acc} | |
act = page.at('#SearchResultsForm').attr('action') | |
act = act[2..act.length] | |
action = URI.join("http://www.ucaoa.org/searchserver/", act).to_s | |
param_name = page_num.to_i > 9 ? "SearchResultsGrid$ctl29$ctl#{page_num.to_s}" : "SearchResultsGrid$ctl29$ctl0#{page_num.to_s}" | |
body['__EVENTTARGET'] = param_name | |
body['__EVENTARGUMENT'] = "" | |
headers = { | |
'Accept' => 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', | |
'Cookie' => 'ASP.NET_SessionId=nfdzr1y3s3oe2hgb0uumd30y; ymssc=search_rsss06; ASPSession=Owner=C; ASPSESSIONIDAARRTQRA=JIBOOPDBAGEHKKMPNFIBDMNL; apvc=saas749', | |
'Upgrade-Insecure-Requests' => '1', | |
'User-Agent' => 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' | |
} | |
params = { | |
method: :post, | |
page_type: 'search', | |
body: body.inject([]){|acc,c| acc+["#{CGI.escape(c[0])}=#{CGI.escape(c[1].to_s)}"]}.join('&') | |
body: body | |
} | |
t_2 = Typhoeus.get action, headers: headers, body: params | |
page_2 = Nokogiri::HTML t_2.body | |
page_2.search('a').each do |a| | |
if a.attr('href').include? '/members/?id=' | |
links.push(a.attr('href')) | |
end | |
end | |
end | |
links.uniq.count |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment