def mmdc(input_text, file_format='svg', flags=dict()):
if not isinstance(flags, dict):
raise Exception("mmdc: flags not a dictionary")
if not isinstance(file_format, str) or re.search(r'[^a-z]', file_format) or len(file_format) == 0:
raise Exception("mmdc: invalid file format")
if not isinstance(input_text, str):
input_text = str(input_text)
sys.stderr.write("Writing:\n" + input_text + "\n")
input_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="w", suffix=".mmd", delete=False)
input_file.write(input_text)
input_file.close()
output_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="w", suffix="." + file_format, delete=False)
output_file.close()
commands = [get_config('mmdc path', 'mmdc'), '-p', os.path.join(expanduser("~"), 'puppeteer-config.json'), '-i', input_file.name, '-o', output_file.name]
for key, val in flags.items():
commands.append('-' + str(key))
commands.append(repr(str(val)))
sys.stderr.write("Commands are: " + " ".join(commands) + "\n")
try:
output = subprocess.check_output(commands, stderr=subprocess.STDOUT).decode()
except subprocess.CalledProcessError as err:
output = err.output.decode()
raise Exception("mmdc: there was an error. " + output)
if os.path.getsize(output_file.name) == 0:
raise Exception("mmdc: the command did not produce any output. " + output)
obj = DAFile()
obj.set_random_instance_name()
obj.initialize(extension=file_format)
obj.copy_into(output_file.name)
obj.commit()
return obj
def mmdc(input_text, file_format='svg', flags=dict()):
if not isinstance(flags, dict):
raise Exception("mmdc: flags not a dictionary")
if not isinstance(file_format, string_types) or re.search(r'[^a-z]', file_format) or len(file_format) == 0:
raise Exception("mmdc: invalid file format")
if not isinstance(input_text, string_types):
input_text = text_type(input_text)
sys.stderr.write("Writing:\n" + input_text + "\n")
input_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="w", suffix=".mmd", delete=False)
input_file.write(input_text)
input_file.close()
output_file = tempfile.NamedTemporaryFile(prefix="datemp", mode="w", suffix="." + file_format, delete=False)
output_file.close()
commands = [get_config('mmdc path', 'mmdc'), '-p', os.path.join(expanduser("~"), 'puppeteer-config.json'), '-i', input_file.name, '-o', output_file.name]
for key, val in flags.items():
commands.append('-' + str(key))
commands.append(repr(str(val)))
sys.stderr.write("Commands are: " + " ".join(commands) + "\n")
try:
output = subprocess.check_output(commands, stderr=subprocess.STDOUT).decode()
except subprocess.CalledProcessError as err:
output = err.output.decode()
raise Exception("mmdc: there was an error. " + output)
if os.path.getsize(output_file.name) == 0:
raise Exception("mmdc: the command did not produce any output. " + output)
obj = DAFile()
obj.set_random_instance_name()
obj.initialize(extension=file_format)
obj.copy_into(output_file.name)
obj.commit()
return obj
def fetch_revenue_info(self):
revenue_page = DAFile()
revenue_page.set_random_instance_name()
revenue_page.initialize(filename='Department-of-Revenue.pdf')
address_escaped = urllib.quote(self.one_line())
step = ['casperjs', DAStaticFile(filename='revenue.js').path(), address_escaped, revenue_page.path()]
result = subprocess.call(step)
if result != 0:
time.sleep(5)
result = subprocess.call(step)
if result != 0:
raise Exception("Failed to fetch Revenue information")
revenue_page.retrieve()
revenue_page.commit()
self.revenue_page = revenue_page
def make_event(title=None,
location=None,
description=None,
begin_date=None,
begin_time=None,
end_date=None,
end_time=None,
organizer=None,
attendees=[]):
if title is None:
raise Exception("make_event: a title parameter is required")
if begin_date is None:
raise Exception("make_event: a begin_date parameter is required")
if begin_time is None:
raise Exception("make_event: a begin_time parameter is required")
if end_date is None:
raise Exception("make_event: an end_date parameter is required")
if end_time is None:
raise Exception("make_event: an end_time parameter is required")
c = Calendar()
e = Event()
if organizer is not None:
e.organizer = Organizer(common_name=organizer.name.full(),
email=organizer.email)
if len(attendees) > 0:
e.attendees = [
Attendee(common_name=attendee.name.full(), email=attendee.email)
for attendee in attendees
]
e.name = str(title)
e.begin = as_datetime(
begin_date.replace_time(begin_time),
timezone='UTC').format_datetime('yyyy-MM-dd hh:mm:ss')
e.end = as_datetime(end_date.replace_time(end_time),
timezone='UTC').format_datetime('yyyy-MM-dd hh:mm:ss')
if location not in (None, ''):
e.location = str(location)
if description not in (None, ''):
e.description = str(description)
c.events.add(e)
c.events
ics_file = DAFile('ics_file')
ics_file.set_random_instance_name()
ics_file.initialize(filename="event.ics", mimetype="text/calendar")
with open(ics_file.path(), 'w') as f:
f.write(str(c))
ics_file.commit()
return ics_file
def download_file(filename, folder_name):
file_id = get_file_id(filename, folder_name)
if file_id is None:
raise Exception("The file was not found")
the_file = DAFile()
the_file.set_random_instance_name()
the_file.initialize(filename=filename)
service = api.drive_service()
with open(the_file.path(), 'wb') as fh:
response = service.files().get_media(fileId=file_id)
downloader = apiclient.http.MediaIoBaseDownload(fh, response)
done = False
while done is False:
status, done = downloader.next_chunk()
the_file.commit()
return the_file
def vyhlaskaText(id):
r = requests.get('https://sbirkapp.gov.cz/detail/' + id + '/text')
if "pdf" in r.headers['content-type']:
thefile = DAFile("thefile")
thefile.initialize(filename="vyhlaska.pdf", extension="pdf")
thefile.write(r.content, binary="true")
return (ocr_file(thefile, language="cs"))
elif "docx" in r.headers['content-type']:
obsah = []
doc = docx.Document(io.BytesIO(r.content))
for para in doc.paragraphs:
obsah.append(para.text)
return ('\n'.join(obsah))
elif "doc" == r.headers[
'content-type'] or "application/msword" == r.headers[
'content-type']:
r = requests.post(
'https://hook.integromat.com/7nmnpym8m6g0byshhd2d7e6jh6y8gcjn?url=https://sbirkapp.gov.cz/detail/'
+ id + '/text')
text = r.content.decode('utf-8')
return (text)
elif "odt" in r.headers['content-type']:
try:
with tempfile.NamedTemporaryFile() as tmp:
r = requests.get('https://sbirkapp.gov.cz/detail/' + id +
'/text')
tmp.write(r.content)
text = textract.process(tmp.name,
extension='odt').decode('utf-8')
return (text)
except Exception as e:
return (e)
else:
return (r.headers['content-type'])
def as_dafile(self, file_obj = None):
"""Modify the DAFile file_obj with the contents of the URL and filename in the LazyFile, or if none given, return a new DAFile."""
if file_obj is None:
file_obj = DAFile()
file_obj.initialize(filename=self.filename)
file_obj.from_url(self.url)
file_obj.commit()
return file_obj
else:
file_obj.initialize(filename=self.filename)
file_obj.from_url(self.url)
file_obj.commit()
def as_dafile(self, file_obj=None, o365=None):
"""Modify the DAFile file_obj with the contents of the URL and filename in the LazyFile, or if none given, return a new DAFile."""
if o365:
o365.refresh_download_link(self)
if file_obj is None:
file_obj = DAFile()
file_obj.title = self.primaryTitle()
file_obj.initialize(filename=self.filename)
file_obj.from_url(self.url)
file_obj.commit()
return file_obj
else:
file_obj.initialize(filename=self.filename)
file_obj.title = self.primaryTitle()
file_obj.from_url(self.url)
file_obj.commit()
def fetch_google_street_view_image(self):
google_api_key = get_config('google', dict()).get('api key', None)
if google_api_key is None:
raise Exception("No Google Maps API key")
street_view_image = tempfile.NamedTemporaryFile(prefix="datemp", suffix=".png")
google_address = urllib.quote(self.one_line(with_city_state=True))
the_url = 'https://maps.googleapis.com/maps/api/streetview?size=640x640&location=' + google_address + '&key=' + google_api_key
try:
urllib.urlretrieve(the_url, street_view_image.name)
except Exception as err:
raise Exception('Error retrieving Google Street View image')
street_view_pdf = DAFile()
street_view_pdf.set_random_instance_name()
street_view_pdf.initialize(filename="Google_Street_View.pdf")
png_to_pdf(street_view_image.name, street_view_pdf.path())
street_view_pdf.retrieve()
street_view_pdf.commit()
street_view_png = DAFile()
street_view_png.set_random_instance_name()
street_view_png.initialize(filename="Google_Street_View.png")
street_view_png.copy_into(street_view_image.name)
street_view_png.retrieve()
street_view_png.commit()
self.google_street_view_pdf = street_view_pdf
self.google_street_view_image = street_view_png
def get_pdf(self, indexno=None, fileno=None, pageno=None, filename=None):
api_key = get_config('docket api key')
if indexno is None or fileno is None or pageno is None or filename is None:
raise Exception("get_pdf: invalid input")
new_file = DAFile()
new_file.set_random_instance_name()
new_file.initialize(filename=filename)
new_file.from_url("https://docket.philalegal.org/docketinfo?docketnum=" + str(self.docketnum) + '&indexno=' + str(indexno) + '&fileno=' + str(fileno) + '&pageno=' + str(pageno) + "&key=" + api_key)
#new_file.make_pngs()
new_file.retrieve()
new_file.commit()
return new_file
def fetch_opa_info(self):
homestead = tempfile.NamedTemporaryFile(prefix="datemp", suffix=".txt")
opa_image = tempfile.NamedTemporaryFile(prefix="datemp", suffix=".png")
avi_image = tempfile.NamedTemporaryFile(prefix="datemp", suffix=".png")
opa_page = DAFile()
opa_page.set_random_instance_name()
opa_page.initialize(filename='OPA.pdf')
avi_page = DAFile()
avi_page.set_random_instance_name()
avi_page.initialize(filename='AVI.pdf')
address_escaped = urllib.quote(self.one_line())
step = ['casperjs', DAStaticFile(filename='opa-png.js').path(), address_escaped, opa_image.name, avi_image.name, homestead.name]
sys.stderr.write(" ".join(step) + "\n")
result = subprocess.call(step)
if result != 0:
time.sleep(5)
result = subprocess.call(step)
if result != 0 and self.address.get('opa', None) is not None:
step = ['casperjs', DAStaticFile(filename='opa-account-png.js').path(), self.address['opa'], opa_image.name, avi_image.name, homestead.name]
result = subprocess.call(step)
if result != 0:
time.sleep(5)
result = subprocess.call(step)
if result != 0:
raise Exception("Failed to fetch OPA information")
png_to_pdf(opa_image.name, opa_page.path())
#opa_page.make_pngs()
opa_page.retrieve()
opa_page.commit()
png_to_pdf(avi_image.name, avi_page.path())
#avi_page.make_pngs()
avi_page.retrieve()
avi_page.commit()
self.opa_page = opa_page
self.avi_page = avi_page
homestead.seek(0, 0)
self.has_homestead = False if homestead.read() == "No" else True
def fetch_philadox_info(self):
r = DARedis()
while r.get('using_philadox') is not None:
time.sleep(5)
pipe = r.pipeline()
pipe.set('using_philadox', 1)
pipe.expire('using_philadox', 120)
pipe.execute()
tdir = tempfile.mkdtemp()
info = urllib.quote(json.dumps([self.address['number'], self.address['direction'], self.address['street'], tdir, get_config('philadox username'), get_config('philadox password')]))
step = ['casperjs', DAStaticFile(filename='eagleweb.js').path(), info]
result = subprocess.call(step)
r.delete('using_philadox')
if result != 0:
raise Exception("Failed to fetch Philadox information")
outfiles = []
for pdf_file in sorted([f for f in os.listdir(tdir) if f.endswith('.pdf')]):
new_file = DAFile()
new_file.set_random_instance_name()
new_file.initialize(filename=pdf_file)
new_file.copy_into(os.path.join(tdir, pdf_file))
new_file.retrieve()
new_file.commit()
outfiles.append(new_file)
self.philadox_files = outfiles