-
Notifications
You must be signed in to change notification settings - Fork 103
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: Adding North Hertfordshire District Council
fix: #1028
- Loading branch information
Showing
3 changed files
with
113 additions
and
0 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
93 changes: 93 additions & 0 deletions
93
uk_bin_collection/uk_bin_collection/councils/NorthHertfordshireDistrictCouncil.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 +1,93 @@ | ||
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_postcode = kwargs.get("postcode") | ||
user_paon = kwargs.get("paon") | ||
check_postcode(user_postcode) | ||
check_paon(user_paon) | ||
bindata = {"bins": []} | ||
|
||
URI = "https://uhtn-wrp.whitespacews.com/" | ||
|
||
session = requests.Session() | ||
|
||
# get link from first page as has some kind of unique hash | ||
r = session.get( | ||
URI, | ||
) | ||
r.raise_for_status() | ||
soup = BeautifulSoup(r.text, features="html.parser") | ||
|
||
alink = soup.find("a", text="Find my bin collection day") | ||
|
||
if alink is None: | ||
raise Exception("Initial page did not load correctly") | ||
|
||
# greplace 'seq' query string to skip next step | ||
nextpageurl = alink["href"].replace("seq=1", "seq=2") | ||
|
||
data = { | ||
"address_name_number": user_paon, | ||
"address_postcode": user_postcode, | ||
} | ||
|
||
# get list of addresses | ||
r = session.post(nextpageurl, data) | ||
r.raise_for_status() | ||
|
||
soup = BeautifulSoup(r.text, features="html.parser") | ||
|
||
# get first address (if you don't enter enough argument values this won't find the right address) | ||
alink = soup.find("div", id="property_list").find("a") | ||
|
||
if alink is None: | ||
raise Exception("Address not found") | ||
|
||
nextpageurl = URI + alink["href"] | ||
|
||
# get collection page | ||
r = session.get( | ||
nextpageurl, | ||
) | ||
r.raise_for_status() | ||
soup = BeautifulSoup(r.text, features="html.parser") | ||
|
||
if soup.find("span", id="waste-hint"): | ||
raise Exception("No scheduled services at this address") | ||
|
||
u1s = soup.find("section", id="scheduled-collections").find_all("u1") | ||
|
||
for u1 in u1s: | ||
lis = u1.find_all("li", recursive=False) | ||
|
||
date = lis[1].text.replace("\n", "") | ||
bin_type = lis[2].text.replace("\n", "") | ||
|
||
dict_data = { | ||
"type": bin_type, | ||
"collectionDate": datetime.strptime( | ||
date, | ||
"%d/%m/%Y", | ||
).strftime(date_format), | ||
} | ||
bindata["bins"].append(dict_data) | ||
|
||
bindata["bins"].sort( | ||
key=lambda x: datetime.strptime(x.get("collectionDate"), date_format) | ||
) | ||
|
||
return bindata |
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