1
0
personal-data/personal_data/__main__.py

123 lines
3.7 KiB
Python
Raw Normal View History

2023-12-10 23:27:56 +00:00
import requests
import requests_cache
import csv
import datetime
import io
2023-12-10 23:42:51 +00:00
import browsercookie
2023-12-10 23:27:56 +00:00
from frozendict import frozendict
2024-01-28 20:01:50 +00:00
import logging
2024-02-25 00:38:44 +00:00
import cfscrape
2024-01-28 20:01:50 +00:00
logger = logging.getLogger(__name__)
2023-12-10 23:27:56 +00:00
2024-01-28 21:33:30 +00:00
import personal_data.fetchers.playstation
import personal_data.fetchers.crunchyroll
2024-02-25 00:38:44 +00:00
import personal_data.fetchers.psnprofiles
2024-02-25 19:20:37 +00:00
import personal_data.data
CSV_DIALECT = 'one_true_dialect'
csv.register_dialect(CSV_DIALECT, lineterminator = '\n', skipinitialspace = True)
2023-12-10 23:27:56 +00:00
2024-02-25 19:20:37 +00:00
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):
2023-12-10 23:27:56 +00:00
dicts = []
2024-01-28 21:29:29 +00:00
try:
with open(filename, 'r') as csvfile:
2024-02-25 19:20:37 +00:00
reader = csv.DictReader(csvfile, dialect = CSV_DIALECT)
2024-01-28 21:29:29 +00:00
for row in reader:
2024-02-25 19:20:37 +00:00
for k in list(row.keys()):
row[k] = to_value(row[k])
if row[k] is None:
del row[k]
2024-01-28 21:29:29 +00:00
dicts.append(frozendict(row))
del csvfile
except FileNotFoundError as e:
logger.info('Creating file: %s', filename)
pass
2023-12-10 23:27:56 +00:00
2024-02-25 00:38:44 +00:00
original_num_dicts = len(dicts)
2023-12-10 23:27:56 +00:00
dicts += [frozendict(d) for d in new_dicts]
del new_dicts
2024-02-25 00:38:44 +00:00
fieldnames = []
for d in dicts:
for k in d.keys():
if k not in fieldnames:
fieldnames.append(k)
2024-02-25 19:20:37 +00:00
del k
del d
2024-01-28 21:29:29 +00:00
2024-02-25 19:20:37 +00:00
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))
2023-12-10 23:27:56 +00:00
csvfile_in_memory = io.StringIO()
2024-02-25 19:20:37 +00:00
writer = csv.DictWriter(csvfile_in_memory, fieldnames=fieldnames, dialect = CSV_DIALECT)
2023-12-10 23:27:56 +00:00
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
2024-02-25 00:38:44 +00:00
logger.warning('Extended CSV "%s" from %d to %d lines', filename, original_num_dicts, len(dicts))
2023-12-10 23:27:56 +00:00
2024-01-28 21:29:29 +00:00
STANDARD_HEADERS = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:122.0) Gecko/20100101 Firefox/122.0',
2024-02-25 00:38:44 +00:00
#"Accept": "application/json, text/plain, */*",
2024-01-28 21:29:29 +00:00
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate, br',
}
2023-12-10 23:27:56 +00:00
def main():
2023-12-10 23:42:51 +00:00
cookiejar = browsercookie.firefox()
2024-01-28 21:29:29 +00:00
logger.warning('Got cookiejar from firefox: %s cookies', len(cookiejar))
2024-01-28 20:01:50 +00:00
2024-02-25 00:38:44 +00:00
#session = requests_cache.CachedSession('web_cache', cookies = cookiejar)
session = cfscrape.create_scraper()
2024-01-28 20:01:50 +00:00
for cookie in cookiejar:
session.cookies.set_cookie(cookie)
2024-03-03 15:59:03 +00:00
for scraper_cls in personal_data.data.Scraper.__subclasses__():
scraper = scraper_cls(session)
del scraper_cls
2024-01-28 20:01:50 +00:00
logger.warning('Running scraper: %s', scraper.dataset_name)
2024-02-25 00:38:44 +00:00
result_rows = list()
2024-03-03 15:59:03 +00:00
for result in scraper.scrape():
2024-02-25 00:38:44 +00:00
result_rows.append(result)
del result
2023-12-10 23:27:56 +00:00
extend_csv_file('output/'+scraper.dataset_name, result_rows,
2024-02-25 19:20:37 +00:00
deduplicate_mode = scraper.deduplicate_mode)
2024-02-25 00:38:44 +00:00
logger.warning('Scraper done: %s', scraper.dataset_name)
2024-03-03 15:59:03 +00:00
del scraper
2023-12-10 23:27:56 +00:00
if __name__ == '__main__':
main()