Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix bug where crawl_span (int of num days for crawl span) is overwritten with CrawlSpan object in run_repeated #36

Merged
merged 2 commits into from
Jun 30, 2024
Merged

fix bug where crawl_span (int of num days for crawl span) is overwritten with CrawlSpan object in run_repeated #36

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1e80f9a
fix bug where crawl_span (int of num days for crawl span) is overwrit…
macpd Jun 29, 2024
aaca434
rename CrawlDateSpan -> CrawlDateWindow
macpd Jun 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 10 additions & 10 deletions src/tiktok_api_helper/cli_data_acquisition.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@
_DAYS_PER_ITER = 28
_DEFAULT_CREDENTIALS_FILE_PATH = Path("./secrets.yaml")

CrawlSpan = namedtuple("CrawlSpan", ["start_date", "end_date"])
CrawlDateWindow = namedtuple("CrawlDateWindow", ["start_date", "end_date"])


def run_long_query(config: ApiClientConfig):
Expand Down Expand Up @@ -273,14 +273,14 @@ def print_query(
print(json.dumps(query, cls=QueryJSONEncoder, indent=2))


def make_crawl_span(crawl_span: int, crawl_lag: int) -> CrawlSpan:
"""Returns a CrawlSpan with an end_date crawl_lag days before today, and start_date crawl_span
days before end_date.
def make_crawl_date_window(crawl_span: int, crawl_lag: int) -> CrawlDateWindow:
"""Returns a CrawlDateWindow with an end_date crawl_lag days before today, and start_date
crawl_span days before end_date.
"""
assert crawl_span > 0 and crawl_lag > 0, "crawl_span and crawl_lag must be non-negative"
end_date = date.today() - timedelta(days=crawl_lag)
start_date = end_date - timedelta(days=crawl_span)
return CrawlSpan(start_date=start_date, end_date=end_date)
return CrawlDateWindow(start_date=start_date, end_date=end_date)


@APP.command()
Expand Down Expand Up @@ -335,16 +335,16 @@ def run_repeated(
utils.setup_logging_info_level()

while True:
crawl_span = make_crawl_span(crawl_span=crawl_span, crawl_lag=crawl_lag)
crawl_date_window = make_crawl_date_window(crawl_span=crawl_span, crawl_lag=crawl_lag)
logging.info(
"Starting scheduled run. start_date: %s, end_date: %s",
crawl_span.start_date,
crawl_span.end_date,
crawl_date_window.start_date,
crawl_date_window.end_date,
)
execution_start_time = pendulum.now()
run(
start_date_str=utils.date_to_tiktok_str_format(crawl_span.start_date),
end_date_str=utils.date_to_tiktok_str_format(crawl_span.end_date),
start_date_str=utils.date_to_tiktok_str_format(crawl_date_window.start_date),
end_date_str=utils.date_to_tiktok_str_format(crawl_date_window.end_date),
db_file=db_file,
db_url=db_url,
crawl_tag=crawl_tag,
Expand Down
Loading