Update scrapebotv3.py

strip puntuation marks from case name, to fix the s\o errors with the slash
jobchong · Mar 1, 2016 · 2960f83 · 2960f83
1 parent b86a2a2
commit 2960f83
Showing 1 changed file with 5 additions and 0 deletions.
diff --git a/scrapebotv3.py b/scrapebotv3.py
@@ -222,6 +222,11 @@ def returnListofDocumentURLsonResultspage(bsObj):
             s = session.get(documenturl, headers=headers)
             bsObj = BeautifulSoup(s.content, 'html.parser')
             nameofcase = bsObj.find('span', class_ = "caseTitle").get_text()
+
+            import string
+            for char in string.punctuation: #strip puntuation marks from case name
+                nameofcase = nameofcase.replace(char, " ")
+
             if bsObj.find('span', class_ = 'Citation offhyperlink'):
                 citation = bsObj.find('span', class_ = 'Citation offhyperlink').get_text()
             combinednameofcase = (nameofcase + citation)