[email protected]

FdaMedDeviceRecalls

import urllib

from BeautifulSoup import BeautifulSoup

URL = 'http://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfRES/res.cfm'

Web_cnx = urllib.urlopen(URL)

html = web_cnx.read()

soup = BeautifulSoup(html)
	

	###Below are just elements - and excuse the substitute SQL. No idea how to proceed:

FIND input name = 'postdatefrom' 

FIND input name = 'postdateto'

	(NEED to enter 2-month increments beginning Nov. 2002 BUT months range  28-31 days, so…?)

FIIND name = 'pagenum'

ENTER '500'

FIND name = 'search'

PUSH SEARCH


	###ON next page:

links = soup.find(href WHERE color = 23238e)


for link  in links[1:]:
    data = link.findAll('href')
    link = data[0].text
    print '\t'.join([link])



	### NOW, when all links obtained, PUSH each link. Within Each link:

FIND table WHERE cellpadding='2' AND cellspacing='14'

Input = soup.find('th')
Response = soup.find('td')


	th = 'Date Posted'  ### Do I add underscore when I define those with multiple words?
	
	th = 'RecallNumber'
	
	th = 'Product'
	
	th = 'Code Information'

	th = 'recalling firm/' <br> 'Manufacturer'

	th = 'Consumer Instructions'

	th = 'For Additional Information Contact'

	th = 'reason for' <br> 'Recall'

	th = 'Action'

	th = 'Quantity in Commerce'

	th = 'Distribution'


print '\t'.join([……..])