This commit is contained in:
2025-09-11 16:35:22 +03:00
parent babf491c8e
commit 6920d24a98
6 changed files with 173 additions and 276486 deletions

139
main.py
View File

@@ -8,7 +8,7 @@ import xlwt
import xlrd
import requests
from requests.structures import CaseInsensitiveDict
from bs4 import BeautifulSoup
import aigenerated
@@ -16,75 +16,28 @@ import parser
import translations
import utils
import json
import links_parser
# Общее правило проекта, сначала в координатах идёт ROW а потом COL, нумерация с нуля
FACULTETS = [
"asp", "mag", "fastiv", "fat", "ftkm", "ftpp", "feu", "fevt", "htf", "vkf", "mmf", "fpik"
]
BASE_URL = "https://www.vstu.ru/"
RASP_PREFIX = "https://www.vstu.ru/student/raspisaniya/zanyatiy/index.php?dep="
session = requests.Session()
session.headers = CaseInsensitiveDict(
{
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:132.0) Gecko/20100101 Firefox/132.0",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
"Accept-Language: ru-RU,ru;q=0.8,en-US;q=0.5,en;q=0.3",
"Accept-Encoding": "gzip, deflate",
"Connection": "keep-alive",
"Referer": "http://dump.vstu.ru/",
"Upgrade-Insecure-Requests": "1",
"Priority": "u=0, i",
"Pragma": "no-cache",
"Cache-Control": "no-cach",
}
)
EXCEL_LINKS = {}
filestime = str(round(time.time()))
for facultet in FACULTETS:
url = RASP_PREFIX + facultet
r = session.get(url)
print(f"GET {url}")
soup = BeautifulSoup(r.text, 'html.parser')
excel_pattern = re.compile(r'\.xlsx?$')
# Ищем все теги <a>, у которых атрибут href соответствует нашему паттерну
excel_tags = soup.find_all('a', href=excel_pattern)
excel_links = [tag.get('href') for tag in excel_tags]
# Предположим, вы уже получили excel_links из одного из методов выше
# excel_links = ['../../../upload/raspisanie/z/ОН_ХТФ_1 курс.xlsx', ...]
absolute_links = [urljoin(BASE_URL, relative_link) for relative_link in excel_links]
if facultet not in EXCEL_LINKS.keys():
EXCEL_LINKS[facultet] = set()
for excel_url in absolute_links:
EXCEL_LINKS[facultet].add(excel_url)
print(f"+url {excel_url}")
DEBUG_ONE_FAC = None #'fevt'
result = {}
faileds = []
counter = 0
for facultet in FACULTETS:
counter += 1000
print(f"\n\n-- Факультет '{facultet}' --")
facultet_urls = EXCEL_LINKS[facultet]
for excel_url in facultet_urls:
counter += 1
print(f"\n\n-- Ссылка --")
print(f"{excel_url}")
is_xlsx = excel_url.endswith(".xlsx")
def process_excel_file(facultet, excel_url, counter, timeid):
is_xlsx = excel_url.endswith(".xlsx")
try:
filename = "excels/" + timeid + "_" + facultet + f"_[C{counter}]" + ".xls" + ("x" if is_xlsx else "")
aigenerated.download_file_from_url(excel_url, filename)
try:
filename = "excels/" + facultet + filestime + f"[C{counter}]" + ".xls" + ("x" if is_xlsx else "")
aigenerated.download_file_from_url(excel_url, filename)
reader = translations.create_reader(filename)
reader = translations.create_reader(filename)
print("Reader info")
print(reader.info())
while True:
print(f"Parsing sheet №{reader.get_sheet_index()+1}")
parser.LOGGING = False
prs = parser.Parser(reader)
prs.parse()
@@ -92,33 +45,67 @@ for facultet in FACULTETS:
if group_name in result.keys():
print(f" -- WTF -- Doubled groups -- name: {group_name}")
continue
gr = result[group_name] = prs.groups[group_name]
gr['facultet'] = facultet
gr['data_source'] = excel_url.split("/")[-1]
gr['parser_debug'] = {
"C_COUNTER": counter,
"timestime": filestime,
"timeid": timeid,
"excel_url": excel_url,
"reader_info": reader.info(),
"reader_sheet_index": reader.get_sheet_index(),
"filename": filename
}
print(f"Populates {len(prs.groups)} groups to result")
print(f"Populates {len(prs.groups)} groups to result: " + " ".join(prs.groups.keys()))
except Exception as e:
print(f"Error while {excel_url}")
print(e)
traceback.print_exc()
faileds.append({
"ex": e,
"fac": facultet,
"url": excel_url
})
if not reader.has_next_sheet():
print("File ended")
break
else:
reader.next_sheet()
print("Next sheet!")
json.dump(result, open('result.json', 'w'), indent=2, ensure_ascii=False)
except Exception as e:
print(f"Error while {excel_url}")
print(e)
traceback.print_exc()
faileds.append({
"ex": e,
"fac": facultet,
"url": excel_url
})
print("Faileds:")
print(faileds)
print("Saved to result.json")
result = {}
faileds = []
def main():
EXCEL_LINKS = links_parser.parse_links(FACULTETS if DEBUG_ONE_FAC is None else [DEBUG_ONE_FAC])
counter = 0
timeid = str(round(time.time()))
for facultet in EXCEL_LINKS.keys():
counter += 1000
print(f"\n\n-- Факультет '{facultet}' --")
facultet_urls = EXCEL_LINKS[facultet]
for excel_url in facultet_urls:
counter += 1
print(f"\n\n-- Ссылка --")
print(f"{excel_url}")
print("Start processing excel file")
process_excel_file(facultet, excel_url, counter, timeid)
print("Excel file processing done!")
print("Saving result.json")
json.dump(result, open('result.json', 'w'), indent=2, ensure_ascii=False)
print("Saved to result.json")
print("Faileds:")
print(faileds)
if __name__ == "__main__":
main()
print("Bye!")