text[@top="224"and @font="2"]

paulbradshaw · Jan 18, 2017 · 08b40e0 · 08b40e0 · font · Jan 18, 2017
1 parent 313e0fa
commit 08b40e0
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/scraper.py b/scraper.py
@@ -38,7 +38,7 @@ def scrapepdf(url):
   record['schoolname'] = schoolname[0].text.encode('ascii', 'ignore')
 
   #Now the date, which is in <text top="224" left="661" width="147" height="18" font="2"
-  dateinspected = pdfroot.findall('.//text[@top="224"]')
+  dateinspected = pdfroot.findall('.//text[@top="224"and @font="2"]')
   for i in dateinspected:
     if i is not None:
       print 'DATE MATCH? ', i.text.encode('ascii','ignore')