Mercurial > repos > bitlab > plidflow

diff PLIDflow/scripts/scrapPubChem.py @ 6:795e11fac81b draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Included new tools for standardization
author bitlab
date Wed, 22 Apr 2020 06:12:00 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/PLIDflow/scripts/scrapPubChem.py	Wed Apr 22 06:12:00 2020 -0400
@@ -0,0 +1,94 @@
+from requests import Session
+from robobrowser import RoboBrowser
+from pprint import pprint
+from bs4 import BeautifulSoup
+from time import sleep
+import random
+import json
+import csv
+import time
+import re
+import gc
+import time
+import sys
+
+def main():
+	# User information
+
+
+	# REMEMBER TO PUT THE INPUT ARGUMENT WITH DOUBLE QUOTES
+	if (len(sys.argv) != 2):
+                print >> sys.stderr, "ERROR: Missing input chain"
+		exit()
+
+	chain = str(sys.argv[1])
+
+	finished = 0
+
+	while finished == 0:
+
+		try:
+	
+			#chain = 'Nc1nc(NC2CC2)c2ncn([C@@H]3C[C@H](CO)C=C3)c2n1'
+			url = 'https://pubchem.ncbi.nlm.nih.gov/standardize/standardize.cgi'
+
+			# Create session and browser
+			session = Session()
+			browser = RoboBrowser(session=session,history=False, parser="html5lib")
+			browser.open(url)
+
+			form = browser.get_form(action=re.compile(r'standardize'))
+
+			#print(form.fields)
+
+			form['structure'] = 'smiles'
+			form['structuresmiles'] = chain
+
+			#print(len(list(form.submit_fields.items(multi=True))))
+			#print(list(form.submit_fields.items(multi=True)))
+			#print(' FORM action1 name: ', list(form.submit_fields.items(multi=True))[0])
+			#print(' FORM action1 name: ', list(form.submit_fields.items(multi=True))[1])
+
+			submit_field = form['submitjob']
+			submit_field.value = 'Authorize'
+			#print(form)
+			res = browser.submit_form(form, submit=submit_field)
+			parsedbrowser = str(browser.parsed)
+			#print(parsedbrowser)
+	
+			parsedbrowser = parsedbrowser.replace("<html>", "")
+			parsedbrowser = parsedbrowser.replace("<head>", "")
+			parsedbrowser = parsedbrowser.replace("</head>", "")
+			parsedbrowser = parsedbrowser.replace("</html>", "")
+			parsedbrowser = parsedbrowser.replace("<body>", "")
+			parsedbrowser = parsedbrowser.replace("</body>", "")
+
+			badpos = parsedbrowser.find('Output Log:')
+			if(badpos != -1):
+				print >> sys.stderr, parsedbrowser[badpos:]
+			else:
+				parsedbrowser = parsedbrowser.replace("\n", "")
+				print(parsedbrowser)
+
+
+
+			del browser
+			gc.collect()
+
+			finished = 1
+
+
+		except Exception as ex:
+
+			finished = 0
+			time.sleep(5)
+
+
+
+
+	
+
+
+if __name__ == "__main__":
+	main()
+