User:BogBot/Source code/Task 03: Difference between revisions

Revision as of 07:06, 23 July 2011

Revision as of 20:35, 24 July 2011

Line 131:

import csv

import string

# Included for bot exclusion compliance (see http://en.wikipedia.org/wiki/Template:Bots)

# compiled regular expression

user = "BogBot"

Line 144 ⟶ 139:

regexp_drug_infobox = re.compile(r"\{\{\s*(Drugbox|drugbox)\s*(?P<PARAMS>.+)\s*\}\}\s*", re.DOTALL)

regexp_param = re.compile(r"^\s?\|\s?(?P<PARAM>\S+)\s?=\s?(?P<VALUE>.+)$")

# Included for bot exclusion compliance (see http://en.wikipedia.org/wiki/Template:Bots)

def Allowbots(text):

if (regexp_ab.search(text)):

Line 159 ⟶ 155:

drug_data = csv.reader(open('/Users/BogBot/progs/pywikipedia/drugbox/drug_links_agumented.csv', 'rU'), dialect='excel')

# drugs.com root links:

roots = [("monograph","http://www.drugs.com/monograph/"), ("CDI","http://www.drugs.com/cdi/"), ("CONS","http://www.drugs.com/cons/"), ("MTM","http://www.drugs.com/mtm/"), ("parent","http://www.drugs.com/")]

for row in drug_data:

Line 195:

result_drug_infobox = regexp_drug_infobox.search(text)

if result_drug_infobox:

# print "found it!"

parameters = result_drug_infobox.group('PARAMS')

current_parameters = {}

Line 208:

current_parameters[parameter] = value

# print "INN: ", INN

if INN in drugbank_data:

data = drugbank_data[INN]

Line 228:

# print "merck tradenames: ", merck_tradenames

# print "current tradenames: ", current_tradenames

# print "new tradenames: ", current_parameters['tradename']

# test web page, returns "200" if OK:

Line 246:

# | Drugs.com = <!-- link to Drugs.com monograph, e.g., "lisinopril" that links to "http://www.drugs.com/monograph/lisinopril.html" -->

stems = []

INN_html = string.lower(string.replace(INN, " ", "_"))

drugnames = []

link = "http://www.drugs.com/monograph/" + INN_html + ".html"

drugnames.append(INN)

if urllib.urlopen(link).getcode() == 200: # test link status to make sure it is good before assigning parameter

for tradename in new_tradenames:

current_parameters['Drugs.com'] = INN_html

drugnames.append(tradename)

# print "Drugs.com: ", current_parameters['Drugs.com']

for drugname in drugnames:

drugname = string.lower(drugname)

if (string.find(tradename, " ") > 0):

INN_html = string stems.lowerappend(string.replace(INNdrugname, " ", "_"))

stems.append(string.replace(drugname, " ", "-"))

else:

stems.append(drugname)

try:

for root in roots:

for stem in stems:

link = root[1] + stem + ".html"

# print "attempted Drugs.com link: ", link

if urllib.urlopen(link).getcode() == 200: # test link status to make sure it is good before assigning parameter

current_parameters['Drugs.com'] = "{{drugs.com|" + root[0] + "|" + stem + "}}"

raise StopIteration()

# print "Drugs.com: ", current_parameters['Drugs.com'] = INN_html

except StopIteration:

pass

# for parameter, value in current_parameters.iteritems():

Line 407 ⟶ 427:

# replace original drugbox with new drugbox

new_text = re.sub(regexp_drug_infobox, new_drugbox, text)

# print new_text

page.put(new_text, comment='populated clinical fields in drugbox', watchArticle = None, minorEdit = True)