def download(self, path=None):
response = session.get(self.pdf_url, stream=True)
response.raise_for_status()
if path is None:
path = Path(f"{self.publication_number}.pdf")
with path.open("wb") as f:
for chunk in response.iter_content(chunk_size=512 * 1024):
if chunk: # filter out keep-alive new chunks
f.write(chunk)
return path
def get_page(self, page_no):
params = self.get_query(page_no)
response = session.get(
self.url,
params=params,
verify=False,
headers={"Accept": "application/xml"},
)
text = response.text
self._len, page = self.parser.parse(text)
return page
def fields(self):
if not hasattr(self.__class__, "_fields"):
url = "https://ped.uspto.gov/api/search-fields"
response = session.get(url)
if not response.ok:
raise ValueError("Can't get fields!")
raw = response.json()
output = {
inflection.underscore(key): value
for (key, value) in raw.items()
}
self.__class__._fields = output
return self.__class__._fields
def is_online(self):
with session.cache_disabled():
response = session.get("https://ped.uspto.gov/api/search-fields")
if response.ok:
return True
elif "requested resource is not available" in response.text:
raise NotAvailableException(
"Patent Examination Data is Offline - this is a USPTO problem"
)
elif "attempt failed or the origin closed the connection" in response.text:
raise NotAvailableException(
"The Patent Examination Data API is Broken! - this is a USPTO problem"
)
else:
raise NotAvailableException("There is a USPTO problem")
def download(self, path=".", include_appl_id=True):
if str(path)[-4:].lower() == ".pdf":
# If we've been given a specific filename, use it
out_file = Path(path)
elif include_appl_id:
out_file = (
Path(path) /
f"{self.appl_id} - {self.mail_room_date} - {self.code} - {self.description[:40]}.pdf"
)
else:
out_file = (
Path(path) /
f"{self.mail_room_date} - {self.code} - {self.description[:40]}.pdf"
)
with session.get(self.base_url + self.url, stream=True) as r:
r.raise_for_status()
with out_file.open("wb") as f:
for chunk in r.iter_content(chunk_size=8192):
f.write(chunk)
return out_file
def _len(self):
response = session.get(self.url + self.path, params=self.query())
return response.json()["recordTotalQuantity"]
def get_page(self, page_no):
query = self.query()
query["recordStartNumber"] = page_no * self.page_size
response = session.get(self.url + self.path, params=query)
return response.json()["results"]
def _get_results(self) -> Iterator[USApplication]:
url = self.query_url + self.config["filter"]["appl_id"][0]
response = session.get(url)
for item in response.json():
yield self.__schema__.load(item)
def __len__(self):
url = self.query_url + self.config["filter"]["appl_id"][0]
response = session.get(url)
return len(response.json())
def download(self):
"""downloads the PDF associated with the assignment to the current working directory"""
response = session.get(self._image_url, stream=True)
with open(f"{self.id}.pdf", "wb") as f:
f.write(response.raw.read())