def test_parser(path: str) -> None:
path = 'Takeout/' + path
tpath = get_last_takeout(path=path)
assert tpath is not None
results = list(read_html(tpath, path))
# TODO assert len > 100 or something?
print(len(results))
def test_myactivity_search():
path = 'Takeout/My Activity/Search/MyActivity.html'
tpath = get_last_takeout(path=path)
results = list(read_html(tpath, path))
res = (
datetime(year=2018, month=12, day=17, hour=8, minute=16, second=18, tzinfo=pytz.utc),
'https://en.wikipedia.org/wiki/Emmy_Noether&usg=AFQjCNGrSW-iDnVA2OTcLsG3I80H_a6y_Q',
'Emmy Noether - Wikipedia',
)
assert res in results
def _read_myactivity_html(takeout: TakeoutPath, kind: str) -> Iterable[Visit]:
from my.core.kompress import kexists
# TODO glob
# TODO not sure about windows path separators??
spath = 'Takeout/My Activity/' + kind
if not kexists(takeout, spath):
logger.warning(f"{spath} is not present in {takeout}... skipping")
return
logger.info('processing %s %s', takeout, kind)
locator = Loc.file(spath)
from my.google.takeout.html import read_html
for dt, url, title in read_html(takeout, spath):
yield Visit(
url=url,
dt=dt,
locator=locator,
debug=kind,
)