-
Notifications
You must be signed in to change notification settings - Fork 111
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #917 from m26dvd/master
- Loading branch information
Showing
6 changed files
with
316 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
51 changes: 51 additions & 0 deletions
51
uk_bin_collection/uk_bin_collection/councils/CoventryCityCouncil.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,51 @@ | ||
| import requests | ||
| from bs4 import BeautifulSoup | ||
| from dateutil.relativedelta import relativedelta | ||
|
|
||
| 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: | ||
|
|
||
| bindata = {"bins": []} | ||
| curr_date = datetime.today() | ||
|
|
||
| soup = BeautifulSoup(page.content, features="html.parser") | ||
| button = soup.find("a", text="Find out which bin will be collected when.") | ||
|
|
||
| if button["href"]: | ||
| URI = button["href"] | ||
| # Make the GET request | ||
| response = requests.get(URI) | ||
| soup = BeautifulSoup(response.content, features="html.parser") | ||
| divs = soup.find_all("div", {"class": "editor"}) | ||
| for div in divs: | ||
| lis = div.find_all("li") | ||
| for li in lis: | ||
| collection = li.text.split(": ") | ||
| collection_date = datetime.strptime( | ||
| collection[0], | ||
| "%A %d %B", | ||
| ).replace(year=curr_date.year) | ||
| if curr_date.month == 12 and collection_date.month == 1: | ||
| collection_date = collection_date + relativedelta(years=1) | ||
| bin_types = collection[1].split(" and ") | ||
| for bin_type in bin_types: | ||
| dict_data = { | ||
| "type": bin_type, | ||
| "collectionDate": collection_date.strftime("%d/%m/%Y"), | ||
| } | ||
| bindata["bins"].append(dict_data) | ||
| else: | ||
| print("Failed to find bin schedule") | ||
|
|
||
| return bindata |
58 changes: 58 additions & 0 deletions
58
uk_bin_collection/uk_bin_collection/councils/HarboroughDistrictCouncil.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,58 @@ | ||
| import requests | ||
| 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: | ||
|
|
||
| user_uprn = kwargs.get("uprn") | ||
| check_uprn(user_uprn) | ||
| bindata = {"bins": []} | ||
|
|
||
| URI = "https://harborough.fccenvironment.co.uk/detail-address" | ||
|
|
||
| headers = { | ||
| "Content-Type": "application/json", | ||
| "User-Agent": "Mozilla/5.0", | ||
| "Referer": "https://harborough.fccenvironment.co.uk/", | ||
| } | ||
| params = {"Uprn": user_uprn} | ||
| response = requests.post(URI, headers=headers, json=params) | ||
|
|
||
| soup = BeautifulSoup(response.content, features="html.parser") | ||
| bin_collection = soup.find( | ||
| "div", {"class": "blocks block-your-next-scheduled-bin-collection-days"} | ||
| ) | ||
| lis = bin_collection.find_all("li") | ||
| for li in lis: | ||
| try: | ||
| split = re.match(r"(.+)\s(\d{1,2} \w+ \d{4})$", li.text) | ||
| bin_type = split.group(1).strip() | ||
| date = split.group(2) | ||
|
|
||
| dict_data = { | ||
| "type": bin_type, | ||
| "collectionDate": datetime.strptime( | ||
| date, | ||
| "%d %B %Y", | ||
| ).strftime("%d/%m/%Y"), | ||
| } | ||
| bindata["bins"].append(dict_data) | ||
| except: | ||
| continue | ||
|
|
||
| bindata["bins"].sort( | ||
| key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y") | ||
| ) | ||
|
|
||
| return bindata |
59 changes: 59 additions & 0 deletions
59
uk_bin_collection/uk_bin_collection/councils/TeignbridgeCouncil.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,59 @@ | ||
| from bs4 import BeautifulSoup | ||
| from selenium.webdriver.common.by import By | ||
| from selenium.webdriver.support import expected_conditions as EC | ||
| 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: | ||
|
|
||
| user_uprn = kwargs.get("uprn") | ||
| web_driver = kwargs.get("web_driver") | ||
| headless = kwargs.get("headless") | ||
| check_uprn(user_uprn) | ||
| bindata = {"bins": []} | ||
|
|
||
| URI = f"https://www.teignbridge.gov.uk/repositories/hidden-pages/bin-finder?uprn={user_uprn}" | ||
|
|
||
| driver = create_webdriver(web_driver, headless, None, __name__) | ||
| driver.get(URI) | ||
|
|
||
| soup = BeautifulSoup(driver.page_source, features="html.parser") | ||
|
|
||
| collection_dates = soup.find_all( | ||
| "h3" | ||
| ) # Assuming bin types are inside <h3> tags | ||
| bin_type_headers = soup.find_all( | ||
| "div", {"class": "binInfoContainer"} | ||
| ) # Assuming collection dates are inside <p> tags | ||
|
|
||
| # Iterate over the results and extract bin type and collection dates | ||
| for i, date in enumerate(collection_dates): | ||
| collection_date = date.get_text(strip=True) | ||
|
|
||
| bin_types = bin_type_headers[i].find_all("div") | ||
| for bin_type in bin_types: | ||
| dict_data = { | ||
| "type": bin_type.text.strip(), | ||
| "collectionDate": datetime.strptime( | ||
| collection_date, | ||
| "%d %B %Y%A", | ||
| ).strftime("%d/%m/%Y"), | ||
| } | ||
| bindata["bins"].append(dict_data) | ||
|
|
||
| bindata["bins"].sort( | ||
| key=lambda x: datetime.strptime(x.get("collectionDate"), "%d/%m/%Y") | ||
| ) | ||
|
|
||
| return bindata |
72 changes: 72 additions & 0 deletions
72
uk_bin_collection/uk_bin_collection/councils/WatfordBoroughCouncil.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,72 @@ | ||
| import time | ||
|
|
||
| import requests | ||
| 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: | ||
|
|
||
| user_uprn = kwargs.get("uprn") | ||
| check_uprn(user_uprn) | ||
| bindata = {"bins": []} | ||
|
|
||
| SESSION_URL = "https://watfordbc-self.achieveservice.com/authapi/isauthenticated?uri=https%253A%252F%252Fwatfordbc-self.achieveservice.com%252Fen%252Fservice%252FBin_collections%253Faccept%253Dyes%2526consentMessageIds%255B%255D%253D4&hostname=watfordbc-self.achieveservice.com&withCredentials=true" | ||
|
|
||
| API_URL = "https://watfordbc-self.achieveservice.com/apibroker/runLookup" | ||
|
|
||
| data = { | ||
| "formValues": { | ||
| "Address": { | ||
| "echoUprn": {"value": user_uprn}, | ||
| }, | ||
| }, | ||
| } | ||
|
|
||
| headers = { | ||
| "Content-Type": "application/json", | ||
| "Accept": "application/json", | ||
| "User-Agent": "Mozilla/5.0", | ||
| "X-Requested-With": "XMLHttpRequest", | ||
| "Referer": "https://watfordbc-self.achieveservice.com/fillform/?iframe_id=fillform-frame-1&db_id=", | ||
| } | ||
| s = requests.session() | ||
| r = s.get(SESSION_URL) | ||
| r.raise_for_status() | ||
| session_data = r.json() | ||
| sid = session_data["auth-session"] | ||
| params = { | ||
| "id": "5e79edf15b2ec", | ||
| "repeat_against": "", | ||
| "noRetry": "true", | ||
| "getOnlyTokens": "undefined", | ||
| "log_id": "", | ||
| "app_name": "AF-Renderer::Self", | ||
| # unix_timestamp | ||
| "_": str(int(time.time() * 1000)), | ||
| "sid": sid, | ||
| } | ||
| r = s.post(API_URL, json=data, headers=headers, params=params) | ||
| r.raise_for_status() | ||
| data = r.json() | ||
| dispHTML = data["integration"]["transformed"]["rows_data"]["0"]["dispHTML"] | ||
| soup = BeautifulSoup(dispHTML, features="html.parser") | ||
|
|
||
| collections = soup.find_all("li") | ||
| for collection in collections: | ||
| bin_type = collection.find("h3").text | ||
| collection_date = collection.find("strong").text.strip() | ||
| dict_data = {"type": bin_type, "collectionDate": collection_date} | ||
| bindata["bins"].append(dict_data) | ||
|
|
||
| return bindata |
Oops, something went wrong.