mirror of
https://git.ianrenton.com/ian/spothole.git
synced 2026-09-20 22:37:44 +00:00
59 lines
2.2 KiB
Python
59 lines
2.2 KiB
Python
from time import sleep
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
from core.enums import SIGRefType
|
|
from data.sig_ref import SIGRef
|
|
from providers.sigrefdata.file_download_sig_ref_data_provider import FileDownloadSIGRefDataProvider
|
|
|
|
|
|
class PGA(FileDownloadSIGRefDataProvider):
|
|
"""SIG ref data provider for Polish Gmina Award"""
|
|
|
|
POLL_INTERVAL_DAYS = 30
|
|
SIG = "PGA"
|
|
DATA_URL = "http://www.spga.pl/lista_pga2.php"
|
|
|
|
def __init__(self, provider_config):
|
|
super().__init__(self.SIG, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
|
|
|
|
def _http_response_to_data(self, http_response):
|
|
new_data = []
|
|
soup = BeautifulSoup(http_response.text, "html.parser")
|
|
|
|
# Iterate through tables in the page
|
|
for table in soup.find_all("table"):
|
|
header_cells = table.find_all(["th", "td"], limit=10)
|
|
header_texts = [c.get_text(strip=True) for c in header_cells]
|
|
|
|
# If it has "PGA" and "Nazwa" in the header, it's the main data table
|
|
if any("PGA" in t for t in header_texts) and any("Nazwa" in t for t in header_texts):
|
|
# Iterate through all rows except the first
|
|
rows = table.find_all("tr")
|
|
for row in rows[1:]:
|
|
cells = row.find_all("td")
|
|
ref_id = cells[0].get_text(strip=True)
|
|
name = cells[1].get_text(strip=True)
|
|
if not ref_id:
|
|
continue
|
|
|
|
new_data.append(
|
|
SIGRef(
|
|
sig=self.SIG,
|
|
id=ref_id,
|
|
name=name,
|
|
ref_type=SIGRefType.REGION,
|
|
)
|
|
)
|
|
|
|
# Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest
|
|
# of the data in this case
|
|
if self._stop_event.is_set():
|
|
break
|
|
|
|
# Very short pause. This will extend the time to handle sig refs by a few seconds but will ensure some time
|
|
# is available for other threads e.g. the web server.
|
|
sleep(0.001)
|
|
|
|
return new_data
|