refactor chesire_east_gov_uk

mampfes · Jun 4, 2022 · e3c6798 · e3c6798
1 parent 744fa24
commit e3c6798
Show file tree

Hide file tree

Showing 2 changed files with 51 additions and 45 deletions.
diff --git a/...onents/waste_collection_schedule/waste_collection_schedule/source/cheshire_east_gov_uk.py b/...onents/waste_collection_schedule/waste_collection_schedule/source/cheshire_east_gov_uk.py
@@ -1,82 +1,79 @@
-import logging
-
 from datetime import datetime
-from bs4 import BeautifulSoup
 
 import requests
-import urllib.parse
+from bs4 import BeautifulSoup
 from waste_collection_schedule import Collection
 
 TITLE = "cheshireeast.gov.uk"
-DESCRIPTION = (
-    "Source for cheshireeast.gov.uk services for Cheshire East"
-)
+DESCRIPTION = "Source for cheshireeast.gov.uk services for Cheshire East"
 URL = "cheshireeast.gov.uk"
-TEST_CASES = {
-    "houseUPRN" : {"uprn": "100010132071"},
-    "houseAddress": {"postcode":"WA16 0AY", "name_number": "1"}
-}
 
-API_URLS = {
-    "address_search": "https://online.cheshireeast.gov.uk/MyCollectionDay/SearchByAjax/Search",
-    "collection": "https://online.cheshireeast.gov.uk/MyCollectionDay/SearchByAjax/GetBartecJobList?uprn={}",
+
+TEST_CASES = {
+    "houseUPRN": {"uprn": "100010132071"},
+    "houseAddress": {"postcode": "WA16 0AY", "name_number": "1"},
 }
 
-ICONS = {
+ICON_MAP = {
     "General Waste": "mdi:trash-can",
     "Mixed Recycling": "mdi:recycle",
     "Garden Waste": "mdi:leaf",
 }
 
-_LOGGER = logging.getLogger(__name__)
-
 
 class Source:
     def __init__(self, uprn=None, postcode=None, name_number=None):
         self._uprn = uprn
         self._postcode = postcode
-        self.name_number = name_number
+        self._name_number = name_number
 
     def fetch(self):
         session = requests.Session()
-        responseContent=None
 
-        if(self._postcode and self.name_number):
+        if self._postcode and self._name_number:
             # Lookup postcode and number to get UPRN
-            r = session.get(f"https://online.cheshireeast.gov.uk/MyCollectionDay/SearchByAjax/Search?postcode={urllib.parse.quote(self._postcode.encode('utf8'))}&propertyname={self.name_number}")
+            params = {
+                "postcode": self._postcode,
+                "propertyname": self._name_number,
+            }
+            r = session.get(
+                "https://online.cheshireeast.gov.uk/MyCollectionDay/SearchByAjax/Search",
+                params=params,
+            )
+            r.raise_for_status()
             soup = BeautifulSoup(r.text, features="html.parser")
             s = soup.find("a", attrs={"class": "get-job-details"})
-            self._uprn = s['data-uprn']
+            print(s)
+            if s is None:
+                raise Exception("address not found")
+            self._uprn = s["data-uprn"]
+
+        if self._uprn is None:
+            raise Exception("uprn not set")
+
+        params = {"uprn": self._uprn}
+        r = session.get(
+            "https://online.cheshireeast.gov.uk/MyCollectionDay/SearchByAjax/GetBartecJobList",
+            params=params,
+        )
+        r.raise_for_status()
 
-        if self._uprn:
-            r = session.get(f"https://online.cheshireeast.gov.uk/MyCollectionDay/SearchByAjax/GetBartecJobList?uprn={self._uprn}")
-            responseContent = r.text
-
-        soup = BeautifulSoup(responseContent, features="html.parser")
+        soup = BeautifulSoup(r.text, features="html.parser")
         s = soup.find_all("td", attrs={"class": "visible-cell"})
 
         entries = []
 
         for cell in s:
             labels = cell.find_all("label")
-            date = None
-            type = None
             if labels:
-                for i,label in enumerate(labels):
-                    if(i == 1):
-                        date = datetime.strptime(label.text, "%d/%m/%Y")
-                    if(i == 2):
-                        for round_type in ICONS:
-                            if round_type.upper() in label.text.upper():
-                                type = round_type
+                date = datetime.strptime(labels[1].text, "%d/%m/%Y").date()
+                type = labels[2].text.removeprefix("Empty Standard ")
                 entries.append(
-                Collection(
-                     date = date.date(),
-                     t = type,
-                     icon = ICONS.get(type),
-                  )
+                    Collection(
+                        date=date,
+                        t=type,
+                        icon=ICON_MAP.get(type),
+                    )
                 )
-
-        return entries
-
 
+        return entries
diff --git a/doc/source/cheshire_east_gov_uk.md b/doc/source/cheshire_east_gov_uk.md
@@ -10,6 +10,11 @@ waste_collection_schedule:
     - name: cheshire_east_gov_uk
       args:
         uprn: UPRN
+```
+
+```yaml
+waste_collection_schedule:
+    sources:
     - name: cheshire_east_gov_uk
       args:
         postcode: POSTCODE
@@ -37,9 +42,13 @@ waste_collection_schedule:
     - name: cheshire_east_gov_uk
       args:
         uprn: 100010132071
+```
+
+```yaml
+waste_collection_schedule:
+    sources:
     - name: cheshire_east_gov_uk
       args:
         postcode: WA16 0AY
         name_number: 1
 ```
-