def read_browser_history_json(takeout: TakeoutPath) -> Iterable[Visit]:
# TODO replace with my.core.kompress after hpi update (or even use some my. function directly?)
from my.kython.kompress import kexists, kopen
# not sure if this deserves moving to HPI? it's pretty trivial for now
spath = 'Takeout/Chrome/BrowserHistory.json'
if not kexists(takeout, spath):
logger.warning(f"{spath} is not present in {takeout}... skipping")
return
logger.info('processing %s %s', takeout, spath)
# TODO couls also add spath?
locator = Loc.file(takeout)
# TODO this should be supported by HPI now?
j = None
with kopen(takeout, spath) as fo: # TODO iterative parser?
j = json.load(fo)
hist = j['Browser History']
for item in hist:
url = item['url']
time = datetime.utcfromtimestamp(item['time_usec'] /
10**6).replace(tzinfo=pytz.utc)
# TODO any more interesitng info?
yield Visit(
url=url,
dt=time,
locator=locator,
debug='Chrome/BrowserHistory.json',
)
def _read_myactivity_html(takeout: TakeoutPath, kind: str) -> Iterable[Visit]:
# TODO replace with my.core.kompress after hpi update (or even use some my. function directly?)
from my.kython.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,
)
def _read_myactivity_html(takeout: TakeoutPath, kind: str) -> Iterable[Visit]:
from my.kython.kompress import kexists
logger = get_logger()
# 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,
)
def test_kexists(tmp_path: Path) -> None:
assert kexists(str(tmp_path / 'file.zip'), 'path/in/archive')
assert not kexists(str(tmp_path / 'file.zip'), 'path/notin/archive')
# TODO not sure about this?
assert not kexists(tmp_path / 'nosuchzip.zip', 'path/in/archive')
