From a036fe8a0a8bda1629194743f8288ce56476d5a7 Mon Sep 17 00:00:00 2001
From: Michael Bailey <michael.bailey@crypsislabs.com>
Date: Sun, 2 Apr 2017 19:55:40 -0400
Subject: [PATCH] All that's left is to dump entirecampus somewhere sensical
 db-wise

---
 scrape_gmu.py | 66 ++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 58 insertions(+), 8 deletions(-)

diff --git a/scrape_gmu.py b/scrape_gmu.py
index 38d6e23..0519bfa 100644
--- a/scrape_gmu.py
+++ b/scrape_gmu.py
@@ -3,14 +3,64 @@ from bs4 import BeautifulSoup
 
 import requests
 import re
+import json
 
-# Collect the HTML of the laundry page so we can parse it
-r = requests.get('https://housing.gmu.edu/laundry')
+def getLocations():
+	try:
+		# Collect the HTML of the laundry page so we can parse it
+		r = requests.get('https://housing.gmu.edu/laundry')
 
-# Don't just assume the site doesn't time out or shit itself
-if r.status_code == 200:
-	# Isolate Speedqueen URLS
-	for location in re.findall('(?<=quantum\.speedqueen\.com\/wa\/)(.*)(?=\" )',r.text):
-		# Print Location name
-		print location
+		# Don't just assume the site doesn't time out or shit itself
+		if r.status_code == 200:
+			# Isolate Speedqueen URLS
+			locations = re.findall('(?<=quantum\.speedqueen\.com\/wa\/)(.*)(?=\" )',r.text)
+			return locations
 
+		else:
+			return []
+	except requests.exceptions.RequestException:
+		return []
+
+def scrapeLaundry(location):
+	machines = []
+	try:
+		r = requests.get("http://quantum.speedqueen.com/wa/{0}".format(location))
+		if r.status_code == 200:
+			outerparse = BeautifulSoup(r.text, 'html.parser')
+			innerframe = outerparse.iframe['src']
+			innerreq = requests.get(innerframe)
+			if innerreq.status_code == 200:
+				innerparse = BeautifulSoup(innerreq.text, 'html.parser')
+				for list in innerparse.find_all('tr'):
+					try:
+						classtxt = list['class']
+						classed = True
+					except:
+						classed = False
+					if classed == True:
+						bullets = list.find_all('td')
+						for bullet in bullets:
+							if bullet['class'] == ['name']:
+								name = bullet.text
+							if bullet['class'] == ['type']:
+								type = bullet.text
+							if bullet['class'] == ['status']:
+								status = bullet.text
+							if bullet['class'] == ['time']:
+									time = bullet.text
+									obj = [name, type, status, time]
+									if obj[2] != "In use":
+										obj[3] = ""
+									machines.append(obj)
+	except requests.exceptions.RequestException:
+		return []
+	return machines
+
+entirecampus = []
+
+for loc in getLocations():
+	location = []
+	obj = [loc] + scrapeLaundry(loc)
+	entirecampus.append(obj)
+
+print(entirecampus)
\ No newline at end of file
-- 
GitLab