Streamer272/state-soc-cross
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

⚡ Adds parsing 2022 pdf results

Browse Source
This commit is contained in:
Daniel Svitan 2025-04-18 19:33:26 +02:00
parent 96a6810fcd
commit 8e4cac0789
1 changed files with 22 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
get_data.py
View File

@ -44,8 +44,10 @@ if ok.lower() == "n":
counties = ["BA", "TT", "TN", "NR", "ZA", "BB", "PO", "KE"] counties = ["BA", "TT", "TN", "NR", "ZA", "BB", "PO", "KE"]
semifull_counties = ["Bratislavský kraj", "Trnavský kraj", "Trenčianský kraj", "Nitriansky kraj", counties2023 = ["Bratislavský kraj", "Trnavský kraj", "Trenčianský kraj", "Nitriansky kraj",
"Žilinský kraj", "Banskobystrický kraj", "Prešovský kraj", "Košický kraj"] "Žilinský kraj", "Banskobystrický kraj", "Prešovský kraj", "Košický kraj"]
counties2022 = ["Bratislavský", "Trnavský", "Trenčiansky", "Nitriansky",
"Žilinský", "Banskobystrický", "Prešovský", "Košický"]
def extract_2024(cat_str: str, lines: List[str]): def extract_2024(cat_str: str, lines: List[str]):
@ -71,16 +73,26 @@ def extract_2024(cat_str: str, lines: List[str]):
def extract_2023(lines: List[str]): def extract_2023(lines: List[str]):
results = [] results = []
for i in range(len(lines)): for line in lines:
line = lines[i] if line not in counties2023:
if line[0:2] not in ["2.", "3.", "4.", "5.", "6."]:
continue continue
if lines[i-1] not in semifull_counties: results.append(counties[counties2023.index(line)])
print("County not recognized: ", lines[i-1]) if len(results) == 5:
return results
return results
def extract_2022(lines: List[str]):
results = []
for line in lines:
word = line.strip().split(" ")[-1].strip()
if word not in counties2022:
continue continue
results.append(counties[semifull_counties.index(lines[i-1])]) results.append(counties[counties2022.index(word)])
if len(results) == 5: if len(results) == 5:
return results return results
@ -108,7 +120,7 @@ for pdf in pdfs:
cat = int(max(matches[0])) cat = int(max(matches[0]))
cat_str = f"{cat:>02}" cat_str = f"{cat:>02}"
if year != 2023: if year != 2022:
continue continue
id = f"{year}-{cat_str}" id = f"{year}-{cat_str}"
@ -130,6 +142,8 @@ for pdf in pdfs:
results = extract_2024(cat_str, lines) results = extract_2024(cat_str, lines)
case 2023: case 2023:
results = extract_2023(lines) results = extract_2023(lines)
case 2022:
results = extract_2022(lines)
print("got results: ", results) print("got results: ", results)
exit(0) exit(0)