def __init__(self, USPTO_patent_property) -> None:
google_patent_url = "https://patents.google.com/patent/%s" % USPTO_patent_property.number
crawler = handler.Crawler(google_patent_url)
self.__patent_property = PatentAnalyzer.__wrapping_patent_property(
USPTO_patent_property)
self.__parser = crawler.get_beautiful_soup_parser()
self.__head_elem = self.__parser.head
self.__section_elems = self.__parser.find_all('section')
def __try_find_total_patent_count(cls, encoded_query) -> int:
url_for_max_patent_count = cls.__BASIC_URL_PATTERN % (1, 1,
encoded_query)
crawler = handler.Crawler(url_for_max_patent_count)
parser = crawler.get_beautiful_soup_parser()
doc = parser.find_all("strong")
if doc is None:
return -1
else:
return int(doc[len(doc) - 1].get_text())
def __try_find_total_patent_count(self, default_total_size) -> int:
url_for_max_patent_count = self.__BASIC_URL_PATTERN % (1, 1, self.__encoded_query)
print("try auto detect 'the total number of patent'...")
crawler = handler.Crawler(url_for_max_patent_count)
parser = crawler.get_beautiful_soup_parser()
doc = parser.find_all("strong")
if doc is None:
print("auto detect failed...")
return default_total_size
else:
total_patent_count = int(doc[len(doc) - 1].get_text())
print("auto detect success !! total number of patent is %d" % total_patent_count)
return total_patent_count
def build_USPTO_patent_property_list(cls, patent_url) -> List[USPTOPatentProperty]:
patent_property_list = []
parser = handler.Crawler(patent_url).get_beautiful_soup_parser()
table_td = parser.find_all('td', {"valign": "top"})
patent_index = -1
for index, elem in enumerate(table_td):
position = index % 3
data = elem.string.strip()
if position == 0:
patent_index += 1
patent_property_list.append(USPTOPatentProperty())
elif position == 1:
patent_property_list[patent_index].number = data
elif position == 2:
patent_property_list[patent_index].title = data
return patent_property_list