def ParseFile(
self,
knowledge_base: rdf_client.KnowledgeBase,
pathspec: rdf_paths.PathSpec,
filedesc: IO[bytes],
) -> Iterator[rdf_webhistory.BrowserHistoryItem]:
del knowledge_base # Unused.
# TODO(user): Convert this to use the far more intelligent plaso parser.
chrome = ChromeParser()
path = pathspec.CollapsePath()
for timestamp, entry_type, url, data1, _, _ in chrome.Parse(path, filedesc):
if entry_type == "CHROME_DOWNLOAD":
yield rdf_webhistory.BrowserHistoryItem(
url=url,
domain=urlparse.urlparse(url).netloc,
access_time=timestamp,
program_name="Chrome",
source_path=pathspec.CollapsePath(),
download_path=data1)
elif entry_type == "CHROME_VISIT":
yield rdf_webhistory.BrowserHistoryItem(
url=url,
domain=urlparse.urlparse(url).netloc,
access_time=timestamp,
program_name="Chrome",
source_path=pathspec.CollapsePath(),
title=data1)
def Parse(self, stat, file_object, knowledge_base):
"""Parse the History file."""
_, _ = stat, knowledge_base
# TODO(user): Convert this to use the far more intelligent plaso parser.
ie = IEParser(file_object)
for dat in ie.Parse():
yield rdf_webhistory.BrowserHistoryItem(
url=dat["url"],
domain=urlparse.urlparse(dat["url"]).netloc,
access_time=dat.get("mtime"),
program_name="Internet Explorer",
source_urn=file_object.urn)
def ParseFile(self, knowledge_base, pathspec, filedesc):
del knowledge_base # Unused.
# TODO(user): Convert this to use the far more intelligent plaso parser.
ie = IEParser(filedesc)
for dat in ie.Parse():
yield rdf_webhistory.BrowserHistoryItem(
url=dat["url"],
domain=urlparse.urlparse(dat["url"]).netloc,
access_time=dat.get("mtime"),
program_name="Internet Explorer",
source_path=pathspec.CollapsePath())
def Parse(self, stat, file_object, knowledge_base):
"""Parse the History file."""
_, _ = stat, knowledge_base
# TODO(user): Convert this to use the far more intelligent plaso parser.
ff = Firefox3History(file_object)
for timestamp, unused_entry_type, url, title in ff.Parse():
yield rdf_webhistory.BrowserHistoryItem(
url=url,
domain=urlparse.urlparse(url).netloc,
access_time=timestamp,
program_name="Firefox",
source_path=file_object.Path(),
title=title)
def ParseFile(self, knowledge_base, pathspec, filedesc):
del knowledge_base # Unused.
# TODO(user): Convert this to use the far more intelligent plaso parser.
ff = Firefox3History()
for timestamp, unused_entry_type, url, title in ff.Parse(filedesc):
yield rdf_webhistory.BrowserHistoryItem(
url=url,
domain=urlparse.urlparse(url).netloc,
access_time=timestamp,
program_name="Firefox",
source_path=pathspec.CollapsePath(),
title=title)
def Parse(self, stat, file_object, knowledge_base):
"""Parse the History file."""
_ = knowledge_base
# TODO(user): Convert this to use the far more intelligent plaso parser.
chrome = ChromeParser(file_object)
for timestamp, entry_type, url, data1, _, _ in chrome.Parse():
if entry_type == "CHROME_DOWNLOAD":
yield rdf_webhistory.BrowserHistoryItem(
url=url,
domain=urlparse.urlparse(url).netloc,
access_time=timestamp,
program_name="Chrome",
source_urn=file_object.urn,
download_path=data1)
elif entry_type == "CHROME_VISIT":
yield rdf_webhistory.BrowserHistoryItem(
url=url,
domain=urlparse.urlparse(url).netloc,
access_time=timestamp,
program_name="Chrome",
source_urn=file_object.urn,
title=data1)
