uk_bin_collection 0.86.0__tar.gz → 0.86.2__tar.gz

{uk_bin_collection-0.86.0 → uk_bin_collection-0.86.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: uk_bin_collection
-Version: 0.86.0
+Version: 0.86.2
 Summary: Python Lib to collect UK Bin Data
 Author: Robert Bradley
 Author-email: robbrad182@gmail.com

{uk_bin_collection-0.86.0 → uk_bin_collection-0.86.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "uk_bin_collection"
-version = "0.86.0"
+version = "0.86.2"
 description = "Python Lib to collect UK Bin Data"
 readme = "README.md"
 authors = ["Robert Bradley <robbrad182@gmail.com>"]

{uk_bin_collection-0.86.0 → uk_bin_collection-0.86.2}/uk_bin_collection/tests/input.json

@@ -427,6 +427,14 @@
         "wiki_name": "Glasgow City Council",
         "wiki_note": "Replace XXXXXXXX with UPRN."
     },
+    "GloucesterCityCouncil": {
+        "house_number": "111",
+        "postcode": "GL2 0RR",
+        "uprn": "100120479507",
+        "skip_get_url": true,
+        "url": "https://gloucester-self.achieveservice.com/service/Bins___Check_your_bin_day",
+        "wiki_name": "Gloucester City Council"
+    },
     "GuildfordCouncil": {
         "house_number": "THE LODGE, PUTTENHAM HILL HOUSE, PUTTENHAM HILL, PUTTENHAM, GUILDFORD, GU3 1AH",
         "postcode": "GU3 1AH",

uk_bin_collection-0.86.2/uk_bin_collection/uk_bin_collection/councils/GloucesterCityCouncil.py

@@ -0,0 +1,128 @@
+import time
+from datetime import datetime
+
+from bs4 import BeautifulSoup
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver.support.ui import Select
+from selenium.webdriver.support.wait import WebDriverWait
+
+from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+
+# import the wonderful Beautiful Soup and the URL grabber
+
+
+class CouncilClass(AbstractGetBinDataClass):
+    """
+    Concrete classes have to implement all abstract operations of the
+    base class. They can also override some operations with a default
+    implementation.
+    """
+
+    def parse_data(self, page: str, **kwargs) -> dict:
+        driver = None
+        try:
+            page = "https://gloucester-self.achieveservice.com/service/Bins___Check_your_bin_day"
+
+            bin_data = {"bins": []}
+
+            user_uprn = kwargs.get("uprn")
+            user_postcode = kwargs.get("postcode")
+            web_driver = kwargs.get("web_driver")
+            headless = kwargs.get("headless")
+            check_uprn(user_uprn)
+            check_postcode(user_postcode)
+            # Create Selenium webdriver
+            driver = create_webdriver(web_driver, headless, None, __name__)
+            driver.get(page)
+
+            cookies_button = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located((By.ID, "close-cookie-message"))
+            )
+            cookies_button.click()
+
+            without_login_button = WebDriverWait(driver, timeout=15).until(
+                EC.presence_of_element_located(
+                    (By.LINK_TEXT, "or, Continue with no account")
+                )
+            )
+            without_login_button.click()
+
+            iframe_presense = WebDriverWait(driver, 30).until(
+                EC.presence_of_element_located((By.ID, "fillform-frame-1"))
+            )
+
+            driver.switch_to.frame(iframe_presense)
+            wait = WebDriverWait(driver, 60)
+            inputElement_postcodesearch = wait.until(
+                EC.element_to_be_clickable((By.NAME, "find_postcode"))
+            )
+
+            inputElement_postcodesearch.send_keys(user_postcode)
+
+            # Wait for the 'Select address' dropdown to be updated
+            time.sleep(2)
+
+            dropdown = wait.until(
+                EC.element_to_be_clickable((By.NAME, "chooseAddress"))
+            )
+            # Create a 'Select' for it, then select the first address in the list
+            # (Index 0 is "Select...")
+            dropdownSelect = Select(dropdown)
+            dropdownSelect.select_by_value(str(user_uprn))
+
+            # Wait for 'Searching for...' to be added to page
+            WebDriverWait(driver, timeout=15).until(
+                EC.text_to_be_present_in_element(
+                    (By.CSS_SELECTOR, "span[data-name=html1]"), "Searching"
+                )
+            )
+
+            # Wait for 'Searching for...' to be removed from page
+            WebDriverWait(driver, timeout=15).until(
+                EC.none_of(
+                    EC.text_to_be_present_in_element(
+                        (By.CSS_SELECTOR, "span[data-name=html1]"), "Searching"
+                    )
+                )
+            )
+
+            # Even then it can still be adding data to the page...
+            time.sleep(5)
+
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+
+            # This is ugly but there is literally no consistency to the HTML
+            def is_a_collection_date(t):
+                return any("Next collection" in c for c in t.children)
+
+            for next_collection in soup.find_all(is_a_collection_date):
+                bin_info = list(
+                    next_collection.parent.select_one("div:nth-child(1)").children
+                )
+                if not bin_info:
+                    continue
+                bin = bin_info[0].get_text()
+                date = next_collection.select_one("strong").get_text(strip=True)
+                bin_date = datetime.strptime(date, "%d %b %Y")
+                dict_data = {
+                    "type": bin,
+                    "collectionDate": bin_date.strftime(date_format),
+                }
+                bin_data["bins"].append(dict_data)
+
+            bin_data["bins"].sort(
+                key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y")
+            )
+
+        except Exception as e:
+            # Here you can log the exception if needed
+            print(f"An error occurred: {e}")
+            # Optionally, re-raise the exception if you want it to propagate
+            raise
+        finally:
+            # This block ensures that the driver is closed regardless of an exception
+            if driver:
+                driver.quit()
+        return bin_data

uk_bin_collection-0.86.2/uk_bin_collection/uk_bin_collection/councils/WakefieldCityCouncil.py

@@ -0,0 +1,93 @@
+from bs4 import BeautifulSoup
+from uk_bin_collection.uk_bin_collection.common import *
+from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
+from datetime import datetime
+
+class CouncilClass(AbstractGetBinDataClass):
+    """
+    Concrete class to scrape bin collection data.
+    """
+
+    def parse_data(self, page: str, **kwargs) -> dict:
+        driver = None
+        try:
+            # Create Selenium webdriver
+            headless = kwargs.get("headless")
+            driver = create_webdriver(
+                kwargs.get("web_driver"), headless, None, __name__
+            )
+            driver.get(kwargs.get("url"))
+
+            # Make a BS4 object
+            soup = BeautifulSoup(driver.page_source, features="html.parser")
+            soup.prettify()
+
+            data = {"bins": []}
+            # Locate the section with bin collection data
+            sections = soup.find_all("div", {"class": "wil_c-content-section_heading"})
+            
+            for s in sections:
+                if s.get_text(strip=True).lower() == "bin collections":
+                    rows = s.find_next_sibling(
+                        "div", {"class": "c-content-section_body"}
+                    ).find_all("div", class_="tablet:l-col-fb-4 u-mt-10")
+                    
+                    for row in rows:
+                        title_elem = row.find("div", class_="u-mb-4")
+                        if title_elem:
+                            title = title_elem.get_text(strip=True).capitalize()
+                            
+                            # Find all collection info in the same section
+                            collections = row.find_all("div", class_="u-mb-2")
+                            for c in collections:
+                                text = c.get_text(strip=True).lower()
+                                
+                                if "next collection" in text:
+                                    date_text = text.replace("next collection - ", "")
+                                    try:
+                                        next_collection_date = datetime.strptime(
+                                            date_text, "%A, %d %B %Y"
+                                        ).strftime(date_format)
+
+                                        dict_data = {
+                                            "type": title,
+                                            "collectionDate": next_collection_date
+                                        }
+                                        data["bins"].append(dict_data)
+                                    except ValueError:
+                                        # Skip if the date isn't a valid date
+                                        print(f"Skipping invalid date: {date_text}")
+                                    
+                            # Get future collections
+                            future_collections_section = row.find("ul", class_="u-mt-4")
+                            if future_collections_section:
+                                future_collections = future_collections_section.find_all("li")
+                                for future_collection in future_collections:
+                                    future_date_text = future_collection.get_text(strip=True)
+                                    try:
+                                        future_collection_date = datetime.strptime(
+                                            future_date_text, "%A, %d %B %Y"
+                                        ).strftime(date_format)
+
+                                        # Avoid duplicates of next collection date
+                                        if future_collection_date != next_collection_date:
+                                            dict_data = {
+                                                "type": title,
+                                                "collectionDate": future_collection_date
+                                            }
+                                            data["bins"].append(dict_data)
+                                    except ValueError:
+                                        # Skip if the future collection date isn't valid
+                                        print(f"Skipping invalid future date: {future_date_text}")
+
+            # Sort the collections by date
+            data["bins"].sort(
+                key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
+            )
+        except Exception as e:
+            print(f"An error occurred: {e}")
+            raise
+        finally:
+            if driver:
+                driver.quit()
+        return data

uk_bin_collection-0.86.0/uk_bin_collection/uk_bin_collection/councils/WakefieldCityCouncil.py

@@ -1,91 +0,0 @@
-from bs4 import BeautifulSoup
-
-from uk_bin_collection.uk_bin_collection.common import *
-from uk_bin_collection.uk_bin_collection.get_bin_data import AbstractGetBinDataClass
-
-
-# import the wonderful Beautiful Soup and the URL grabber
-class CouncilClass(AbstractGetBinDataClass):
-    """
-    Concrete classes have to implement all abstract operations of the base
-    class. They can also override some operations with a default
-    implementation.
-    """
-
-    def parse_data(self, page: str, **kwargs) -> dict:
-        driver = None
-        try:
-            # Create Selenium webdriver
-            headless = kwargs.get("headless")
-            driver = create_webdriver(
-                kwargs.get("web_driver"), headless, None, __name__
-            )
-            driver.get(kwargs.get("url"))
-
-            # Make a BS4 object
-            soup = BeautifulSoup(driver.page_source, features="html.parser")
-            soup.prettify()
-
-            data = {"bins": []}
-            sections = soup.find_all("div", {"class": "wil_c-content-section_heading"})
-            for s in sections:
-                if s.get_text(strip=True).lower() == "bin collections":
-                    rows = s.find_next_sibling(
-                        "div", {"class": "c-content-section_body"}
-                    ).find_all("div", {"class": "u-mb-8"})
-                    for row in rows:
-                        title = row.find("div", {"class": "u-mb-4"})
-                        collections = row.find_all("div", {"class": "u-mb-2"})
-                        if title and collections:
-                            for c in collections:
-                                if (
-                                    c.get_text(strip=True)
-                                    .lower()
-                                    .startswith("next collection")
-                                ):
-                                    # add next collection
-                                    next_collection_date = datetime.strptime(
-                                        c.get_text(strip=True).replace(
-                                            "Next collection - ", ""
-                                        ),
-                                        "%A, %d %B %Y",
-                                    ).strftime(date_format)
-                                    dict_data = {
-                                        "type": title.get_text(strip=True).capitalize(),
-                                        "collectionDate": next_collection_date,
-                                    }
-                                    data["bins"].append(dict_data)
-                                    # add future collections without duplicating next collection
-                                    future_collections = row.find(
-                                        "ul", {"class": "u-mt-4"}
-                                    ).find_all("li")
-                                    for c in future_collections:
-                                        future_collection_date = datetime.strptime(
-                                            c.get_text(strip=True),
-                                            "%A, %d %B %Y",
-                                        ).strftime(date_format)
-                                        if (
-                                            future_collection_date
-                                            != next_collection_date
-                                        ):
-                                            dict_data = {
-                                                "type": title.get_text(
-                                                    strip=True
-                                                ).capitalize(),
-                                                "collectionDate": future_collection_date,
-                                            }
-                                            data["bins"].append(dict_data)
-
-            data["bins"].sort(
-                key=lambda x: datetime.strptime(x.get("collectionDate"), date_format)
-            )
-        except Exception as e:
-            # Here you can log the exception if needed
-            print(f"An error occurred: {e}")
-            # Optionally, re-raise the exception if you want it to propagate
-            raise
-        finally:
-            # This block ensures that the driver is closed regardless of an exception
-            if driver:
-                driver.quit()
-        return data