From 734d53cb11f01f13e3da6a5ecb92fd8f56981afb Mon Sep 17 00:00:00 2001
From: "Veena Ghorakavi (Emma)" <vvg0009@tamu.edu>
Date: Sun, 20 Oct 2019 06:53:54 -0700
Subject: [PATCH] Added code for downloading files

---
 .DS_Store                            | Bin 6148 -> 6148 bytes
 scripts/drugInfoScript-FILEOUTPUT.py |  22 ++++++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/.DS_Store b/.DS_Store
index f7def658bf4047ac247f5a5da5ea146e303a6691..21345d6ba9d92f6e8686a897770e68ee90f32529 100644
GIT binary patch
delta 136
zcmZoMXfc@J&&aVcU^g=($7UXuG{(t~Se4{c7#J8d|APUL#lXPMP|T3bP{feQP{2^a
zP&~PxRh}D3Y;qaP6k$^f9R*VZqgow>YIAb~9R(9(v&piorqW32Kzhr9i}G^v^U{H)
PGHxt1X57rq@s}R}FbyPb

delta 154
zcmZoMXfc@J&&a+pU^g=(`(_@NG{#&$h75*c215o*23>{%hI}B_V+aD0ML>3zXHI@{
zQcivn0|SEq0|TQtkk<GQ20#`A0~bRsLn=cGTwe)81w#p%o>pW%lk-_sxj!RBHWvP1
K+|17LmmdJ#CoWh3

diff --git a/scripts/drugInfoScript-FILEOUTPUT.py b/scripts/drugInfoScript-FILEOUTPUT.py
index a7a2cb4..76d9b0c 100644
--- a/scripts/drugInfoScript-FILEOUTPUT.py
+++ b/scripts/drugInfoScript-FILEOUTPUT.py
@@ -3,6 +3,24 @@
 import random
 import csv
 import pandas as pd
+from selenium import webdriver
+from selenium.webdriver.common.by import By
+import time
+
+def downloadPathwayCSV(url):
+    driver = webdriver.Firefox()
+    driver.get(url)
+    #download_button = driver.find_element_by_class_name("btn-text")
+    time.sleep(20)
+    download_button = driver.find_element_by_xpath("//button[@id='Download']")
+    time.sleep(20)
+    download_button.click()
+    time.sleep(20)
+    save_button = driver.find_element_by_xpath("//span[.='Save']")
+    time.sleep(20)
+    save_button.click()
+    time.sleep(20)
+    driver.close()
 
 # base url for pubchem
 baseURL = "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/"
@@ -64,6 +82,10 @@
     pathwayURL = "https://pubchem.ncbi.nlm.nih.gov/sdq/sdqagent.cgi?infmt=json&outfmt=csv&query={%22download%22:%22*%22,%22collection%22:%22pathway%22,%22where%22:{%22ands%22:[{%22cid%22:%222244%22},{%22core%22:%221%22}]},%22order%22:[%22name,asc%22],%22start%22:1,%22limit%22:10000000,%22downloadfilename%22:%22CID_" + compoundNum + "_pathway%22}"
     pathway = requests.get(pathwayURL).text
 
+    # This will download the code to the pathway
+    downloadpathwayURL = "https://pubchem.ncbi.nlm.nih.gov/compound/"+ compoundNum +"#section=Pathways&fullscreen=true"
+    pathwayCSV = downloadPathwayCSV(downloadPathwayURL)
+
     pathwayData = pd.read_csv(pathwayURL)
 
     # drop duplicate names in list