# extension = ".session"
# extension = '.win'
extension = '.adr'
url_regex_simple_firefox = '"url":"([^"]*)","'
#url_regex_all_urls = """'(?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|[a-z0-9.\-]+[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)/)(?:[^\s()<>{}\[\]]+|\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\))+(?:\([^\s()]*?\([^\s()]+\)[^\s()]*?\)|\([^\s]+?\)|[^\s`!()\[\]{};:'".,<>?«»“”‘’])|(?:(?<!@)[a-z0-9]+(?:[.\-][a-z0-9]+)*[.](?:com|net|org|edu|gov|mil|aero|asia|biz|cat|coop|info|int|jobs|mobi|museum|name|post|pro|tel|travel|xxx|ac|ad|ae|af|ag|ai|al|am|an|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bm|bn|bo|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cs|cu|cv|cx|cy|cz|dd|de|dj|dk|dm|do|dz|ec|ee|eg|eh|er|es|et|eu|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|Ja|sk|sl|sm|sn|so|sr|ss|st|su|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tp|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|yu|za|zm|zw)\b/?(?!@)))'"""
url_regex_http_https = '.*(http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+).*'
def __init__(self):
self.collection = set()
def parse(self, file):
# pattern = re.compile(SimpleTextParser.url_regex_simple_firefox)
pattern = re.compile(SimpleTextParser.url_regex_http_https)
for i, line in enumerate(file):
for match in re.finditer(pattern, line):
print('Found on line {0}: {1}'.format(i + 1, match.groups()))
self.collection.add(match.group(1))
if __name__ == "__main__":
arg_parser = collector.setup_parser('txt')
argsDict = collector.create_args_dict(arg_parser)
collector = collector.Collector(
SimpleTextParser, argsDict['srcdir'], argsDict['destdir'],
argsDict.get('write_separate_result_files'))
if 'diff' in argsDict:
collector.make_diff(argsDict['diff'])
else:
collector.collect_all()
collector.create_result_file()
if tag == 'a':
pocket_tags = dict(attrs).get('tags')
if not pocket_tags:
pocket_tags = 'without_tag'
url = dict(attrs).get('href')
self.collection.add(url)
if pocket_tags not in self.urls_by_category:
self.urls_by_category[pocket_tags] = set()
self.urls_by_category[pocket_tags].add(url)
def handle_endtag(self, tag):
pass
# print("Encountered an end tag :", tag)
def handle_data(self, data):
pass
# print("Encountered some data :", data)
if __name__ == "__main__":
arg_parser = collector.setup_parser('HTML')
argsDict = collector.create_args_dict(arg_parser)
collector = collector.Collector(HTMLPocketExportParser, argsDict['srcdir'],
argsDict['destdir'],
argsDict['write_separate_result_files'])
if 'diff' in argsDict:
collector.make_diff(argsDict['diff'])
else:
collector.collect_all()
collector.create_result_file()
json_input = json.load(file)
for s in self.id_generator(json_input):
#print(s)
self.collection.add(s)
#pprint(json_input)
def id_generator(self, json_dict):
if isinstance(json_dict, dict):
for k, v in json_dict.items():
if k == "uri":
yield v
elif isinstance(v, dict) or isinstance(v, list):
for id_val in self.id_generator(v):
yield id_val
elif isinstance(json_dict, list):
for listitem in json_dict:
for id_val in self.id_generator(listitem):
yield id_val
if __name__ == "__main__":
arg_parser = collector.setup_parser('json')
argsDict = collector.create_args_dict(arg_parser)
collector = collector.Collector(JsonParser, argsDict['srcdir'], argsDict['destdir'],
argsDict['write_separate_result_files'])
if 'diff' in argsDict:
collector.make_diff(argsDict['diff'])
else:
collector.collect_all()
collector.create_result_file()