1
0
personal-data/personal_data/__main__.py
Jon Michael Aanes a53c1c381d
All checks were successful
Python Package / Package (push) Has been skipped
Improved deduplication
2024-02-25 20:20:37 +01:00

127 lines
3.8 KiB
Python

import requests
import requests_cache
import csv
import datetime
import io
import browsercookie
from frozendict import frozendict
import logging
import cfscrape
logger = logging.getLogger(__name__)
import personal_data.fetchers.playstation
import personal_data.fetchers.crunchyroll
import personal_data.fetchers.psnprofiles
import personal_data.data
CSV_DIALECT = 'one_true_dialect'
csv.register_dialect(CSV_DIALECT, lineterminator = '\n', skipinitialspace = True)
def determine_scrapers():
scrapers = []
#scrapers += personal_data.fetchers.playstation.SCRAPERS
scrapers += personal_data.fetchers.crunchyroll.SCRAPERS
scrapers += personal_data.fetchers.psnprofiles.SCRAPERS
return scrapers
def try_value(fn, s: str) -> any:
try:
return fn(s)
except ValueError:
return None
def to_value(s: str) -> any:
s = s.strip()
if len(s) == 0:
return None
if v := try_value(int, s):
return v
if v := try_value(datetime.date.fromisoformat,s):
return v
if v := try_value(datetime.datetime.fromisoformat,s):
return v
if s.lower() == 'false':
return False
if s.lower() == 'true':
return True
if s.lower() == 'none':
return None
return s
def extend_csv_file(filename: str, new_dicts: dict, deduplicate_mode: personal_data.data.DeduplicateMode):
dicts = []
try:
with open(filename, 'r') as csvfile:
reader = csv.DictReader(csvfile, dialect = CSV_DIALECT)
for row in reader:
for k in list(row.keys()):
row[k] = to_value(row[k])
if row[k] is None:
del row[k]
dicts.append(frozendict(row))
del csvfile
except FileNotFoundError as e:
logger.info('Creating file: %s', filename)
pass
original_num_dicts = len(dicts)
dicts += [frozendict(d) for d in new_dicts]
del new_dicts
fieldnames = []
for d in dicts:
for k in d.keys():
if k not in fieldnames:
fieldnames.append(k)
del k
del d
if deduplicate_mode != personal_data.data.DeduplicateMode.NONE:
dicts = set(dicts)
dicts = sorted(dicts, key = lambda d: tuple(str(d.get(fn, '')) for fn in fieldnames))
csvfile_in_memory = io.StringIO()
writer = csv.DictWriter(csvfile_in_memory, fieldnames=fieldnames, dialect = CSV_DIALECT)
writer.writeheader()
for d in dicts:
writer.writerow(d)
output_csv = csvfile_in_memory.getvalue()
del writer, csvfile_in_memory
with open(filename, 'w') as csvfile:
csvfile.write(output_csv)
del csvfile
logger.warning('Extended CSV "%s" from %d to %d lines', filename, original_num_dicts, len(dicts))
STANDARD_HEADERS = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:122.0) Gecko/20100101 Firefox/122.0',
#"Accept": "application/json, text/plain, */*",
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate, br',
}
def main():
cookiejar = browsercookie.firefox()
logger.warning('Got cookiejar from firefox: %s cookies', len(cookiejar))
#session = requests_cache.CachedSession('web_cache', cookies = cookiejar)
session = cfscrape.create_scraper()
for cookie in cookiejar:
session.cookies.set_cookie(cookie)
for scraper in determine_scrapers():
logger.warning('Running scraper: %s', scraper.dataset_name)
result_rows = list()
for result in scraper.scraper(session):
result_rows.append(result)
del result
extend_csv_file('output/'+scraper.dataset_name, result_rows,
deduplicate_mode = scraper.deduplicate_mode)
logger.warning('Scraper done: %s', scraper.dataset_name)
if __name__ == '__main__':
main()