Added a check to prevent failing on poor html code.

apartment_looker.py

@@ -89,6 +89,10 @@ def do_taeker_things():
 
 
 def do_find_bolig_things():
+
+    def already_seen(already_seens, spec_currently_found) -> bool:
+        return spec_currently_found.id in already_seens
+
     find_bolig_type = namedtuple("Apartment_find_bolig", "link id")
 
     seen_apartments_file_find_bolig = 'seen_apartments_find_bolig.json'
@@ -98,80 +102,83 @@ def do_find_bolig_things():
     r = requests.get("https://www.findbolig.nu/ledigeboliger/liste.aspx?where=Aarhus%208000&rentmax=7000&showrented=1&showyouth=1&showlimitedperiod=1&showunlimitedperiod=1&showOpenDay=0&focus=ctl00_placeholdersidebar_0_txt_where")
 
     soup = BeautifulSoup(r.text, "html5lib")
-    table_body = soup.find(id="GridView_Results").find("tbody")
 
-    all_apartments = []
+    table = soup.find(id="GridView_Results")
-    rows = table_body.find_all('tr')
 
-    concatable_string = "https://www.findbolig.nu/Findbolig-nu/Find%20bolig/Ledige%20boliger/Boligpraesentation"
+    if table is not None:
-    for row in rows[1:]:
+        table_body = soup.find(id="GridView_Results").find("tbody")
-        cols = row.find_all('td')
-        aid = re.search('(aid.+)', cols[0].find('a')['href']).group(0)
-        # Hacky :(
-        id = aid.split("=")[1].split("&")[0]
-        link = concatable_string + "/Boligen.aspx?" + aid
 
-        tmp = find_bolig_type(link, id)
+        all_apartments = []
-        all_apartments.append(tmp)
+        rows = table_body.find_all('tr')
 
-    def already_seen(already_seens, spec_currently_found) -> bool:
+        concatable_string = "https://www.findbolig.nu/Findbolig-nu/Find%20bolig/Ledige%20boliger/Boligpraesentation"
-        return spec_currently_found.id in already_seens
+        for row in rows[1:]:
+            cols = row.find_all('td')
+            aid = re.search('(aid.+)', cols[0].find('a')['href']).group(0)
+            # Hacky :(
+            id = aid.split("=")[1].split("&")[0]
+            link = concatable_string + "/Boligen.aspx?" + aid
 
-    already_seen_locations = [tmp.id for tmp in previous_seen]
+            tmp = find_bolig_type(link, id)
-    for apartment in all_apartments:
+            all_apartments.append(tmp)
-        if not already_seen(already_seen_locations, apartment):
-            print("I've found a new apartment!")
-            if not args.populate_lists:
-                mail_handler.handle(apartment.link)
-            previous_seen.append(apartment)
-        else:
-            print("I've already seen this")
 
 
 
-    with open(seen_apartments_file_find_bolig, 'w', encoding="utf8") as outfile:
+        already_seen_locations = [tmp.id for tmp in previous_seen]
-        json.dump(previous_seen, outfile)
+        for apartment in all_apartments:
+            if not already_seen(already_seen_locations, apartment):
+                print("I've found a new apartment!")
+                if not args.populate_lists:
+                    mail_handler.handle(apartment.link)
+                previous_seen.append(apartment)
+            else:
+                print("I've already seen this")
+
+
+
+        with open(seen_apartments_file_find_bolig, 'w', encoding="utf8") as outfile:
+            json.dump(previous_seen, outfile)
 
 
 
 def do_hestia_things():
 
+    def already_seen(already_seens, spec_currently_found) -> bool:
+        return spec_currently_found.location in already_seens
+
     seen_apartments_file_hestia = 'seen_apartments_hestia.json'
 
     previous_seen = do_old_file_things(seen_apartments_file_hestia, hestia_apartment_type)
 
     r = requests.get("https://www.hestia.as/ledige-lejligheder/?area=266&max=7200")
     soup = BeautifulSoup(r.text, "html5lib")
-    table_body = soup.find(id="sortTable").find("tbody")
 
-    all_apartments = []
+    table = soup.find(id="sortTable")
 
-    rows = table_body.find_all('tr')
+    if table is not None:
-    for row in rows:
+        table_body = soup.find(id="sortTable").find("tbody")
-        link = re.search("(https.+|http.+)", row.get("onclick")).group(0)
-        cols = row.find_all('td')
-        text = [col.get_text() for col in cols]
-        all_apartments.append(hestia_apartment_type(link[:link.find("\'")], *text))
 
+        all_apartments = []
 
-    def already_seen(already_seens, spec_currently_found) -> bool:
+        rows = table_body.find_all('tr')
-        return spec_currently_found.location in already_seens
+        for row in rows:
+            link = re.search("(https.+|http.+)", row.get("onclick")).group(0)
+            cols = row.find_all('td')
+            text = [col.get_text() for col in cols]
+            all_apartments.append(hestia_apartment_type(link[:link.find("\'")], *text))
 
+        already_seen_locations = [tmp.location for tmp in previous_seen]
+        for apartment in all_apartments:
+            if not already_seen(already_seen_locations, apartment):
+                print("I've found a new apartment!")
+                if not args.populate_lists:
+                    mail_handler.handle(apartment.link)
+                previous_seen.append(apartment)
+            else:
+                print("I've already seen this")
 
-    already_seen_locations = [tmp.location for tmp in previous_seen]
+        with open(seen_apartments_file_hestia, 'w', encoding="utf8") as outfile:
-    for apartment in all_apartments:
+            json.dump(previous_seen, outfile)
-        if not already_seen(already_seen_locations, apartment):
-            print("I've found a new apartment!")
-            if not args.populate_lists:
-                mail_handler.handle(apartment.link)
-            previous_seen.append(apartment)
-        else:
-            print("I've already seen this")
-
-
-
-    with open(seen_apartments_file_hestia, 'w', encoding="utf8") as outfile:
-        json.dump(previous_seen, outfile)
 
 
 do_find_bolig_things()