Force bs4 to use lxml instead.

ybhvf · Aug 16, 2015 · b60f343 · b60f343
1 parent 7a84fdb
commit b60f343
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/scraping/new_mexico_tech_banweb.py b/scraping/new_mexico_tech_banweb.py
@@ -159,7 +159,7 @@ def getTerm(semester, subjects, parser):
 		url = "http://banweb7.nmt.edu/pls/PROD/hwzkcrof.P_UncgSrchCrsOff?p_term="+t.getSemester()+"&p_subj="+subjectName.replace(" ", "%20")
 		print url
 		page = urllib2.urlopen(url)
-		soup = BeautifulSoup(page, "html.parser")
+		soup = BeautifulSoup(page, "lxml")
 		trs = soup.findAll("tr")
 		trs = trs[1:] #discard the retarded row that banweb is retarded about
 		print_verbose("adding subject "+subjectName)
@@ -179,7 +179,7 @@ def main(parser):
 
 	page = urllib2.urlopen(url)
 
-	soup = BeautifulSoup(page, "html.parser")
+	soup = BeautifulSoup(page, "lxml")
 
 	path = ""
 	if (type(parser.path) == type("")):