Merge pull request #1478 from fuzzysb/Fix-Oxford-City-Council

fix(OxfordCityCouncil): Fixed Oxford City Council parsing Changes

Author: robbrad

uk_bin_collection/tests/input.json

@@ -1828,8 +1828,8 @@
     "OxfordCityCouncil": {
         "postcode": "OX3 7QF",
         "uprn": "100120820551",
-        "url": "https://www.oxford.gov.uk",
-        "wiki_command_url_override": "https://www.oxford.gov.uk",
+        "url": "https://www.oxford.gov.uk/xfp/form/142",
+        "wiki_command_url_override": "https://www.oxford.gov.uk/xfp/form/142",
         "wiki_name": "Oxford",
         "wiki_note": "You will need to use [FindMyAddress](https://www.findmyaddress.co.uk/search) to find the UPRN.",
         "LAD24CD": "E07000178"

uk_bin_collection/uk_bin_collection/councils/OxfordCityCouncil.py

@@ -21,8 +21,8 @@ def parse_data(self, page: str, **kwargs) -> dict:
         check_postcode(user_postcode)
         bindata = {"bins": []}
 
-        session_uri = "https://www.oxford.gov.uk/mybinday"
-        URI = "https://www.oxford.gov.uk/xfp/form/142"
+        session_uri = "https://www.oxford.gov.uk/xfp/form/142"
+        URI = "https://www.oxford.gov.uk/xfp/form/142#q6ad4e3bf432c83230a0347a6eea6c805c672efeb_0"
 
         session = requests.Session()
         token_response = session.get(session_uri)
@@ -40,15 +40,18 @@ def parse_data(self, page: str, **kwargs) -> dict:
 
         collection_response = session.post(URI, data=form_data)
 
-        collection_soup = BeautifulSoup(collection_response.text, "html.parser")
-        for paragraph in collection_soup.find("div", class_="editor").find_all("p"):
-            matches = re.match(r"^(\w+) Next Collection: (.*)", paragraph.text)
+        soup = BeautifulSoup(collection_response.text, "html.parser")
+        #print(soup)
+
+        for paragraph in soup.find("div", class_="editor").find_all("p"):
+            matches = re.match(r"^Your next (\w+) collections: (.*)", paragraph.text)
             if matches:
                 collection_type, date_string = matches.groups()
+                parts = date_string.split(', ', 1)
                 try:
-                    date = datetime.strptime(date_string, "%A %d %B %Y").date()
+                    date = datetime.strptime(parts[0], "%A %d %B %Y").date()
                 except ValueError:
-                    date = datetime.strptime(date_string, "%A %d %b %Y").date()
+                    date = datetime.strptime(parts[0], "%A %d %b %Y").date()
 
                 dict_data = {
                     "type": collection_type,
@@ -61,3 +64,5 @@ def parse_data(self, page: str, **kwargs) -> dict:
         )
 
         return bindata
+
+

wiki/Councils.md

@@ -2682,7 +2682,7 @@ Note: Replace UPRN in URL with your own UPRN.
 
 ### Oxford City Council
 ```commandline
-python collect_data.py OxfordCityCouncil https://www.oxford.gov.uk -u XXXXXXXX -p "XXXX XXX"
+python collect_data.py OxfordCityCouncil https://www.oxford.gov.uk/xfp/form/142 -u XXXXXXXX -p "XXXX XXX"
 ```
 Additional parameters:
 - `-u` - UPRN