Repository navigation
Expand file tree
/
Copy pathget_FAC.py
More file actions
418 lines (380 loc) · 17.5 KB
/
Copy pathget_FAC.py
File metadata and controls
418 lines (380 loc) · 17.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
#! /usr/bin/env python3.6
# Script for downloading zip files from specific url, extracting pdfs from, then renaming files and uploading via FTP
# Aleksandar Josifoski https://about.me/josifsk
# Script is dependend on selenium, pyvirtualdisplay, BeautifulSoup4, openpyxl
# pip install -U selenium pyvirtualdisplay BeautifulSoup4 openpyxl
# Also is depends on geckodriver. Explanations for geckodriver few lines below
# 2017-02-25
# 2017-03-25: If from or to date in config file is 99/99/9999, substitute system date - this allows the script to be run from a daily cron job
# 2017-05-14: If from date in config file is 99/99/9999, substitute system date minus 2 days - handles backdated uploads
# 2017-08-14: Switched to Chrome, because Firefox Selenium is no longer stable
from pyvirtualdisplay import Display
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.common.keys import Keys
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support.ui import Select
from bs4 import BeautifulSoup
import datetime
import time
import html
import os
import sys
import codecs
import ntpath
import logging
import zipfile
import glob
import openpyxl
import json
from ftplib import FTP
from ftplib import FTP_TLS
from datetime import date
import ntpath
from azure.storage.file import FileService, ContentSettings
with open('FAC_parms.txt', 'r') as fp:
dparameters = json.load(fp)
url = dparameters["url"]
rangefrom = dparameters["rangefrom"]
if rangefrom == "99/99/9999":
prevdaystr = str(date.today() - timedelta(days=2))
rangefrom = prevdaystr[5:7] + "/" + prevdaystr[8:10] + "/" + prevdaystr[0:4]
rangeto = dparameters["rangeto"]
if rangeto == "99/99/9999":
todaystr = str(date.today())
rangeto = todaystr[5:7] + "/" + todaystr[8:10] + "/" + todaystr[0:4]
dir_in = dparameters["dir_in"]
dir_downloads = dparameters["dir_downloads"]
dir_pdfs = dparameters["dir_pdfs"]
fileshortnames = dparameters["fileshortnames"]
sheetShortName = dparameters["sheetShortName"]
headlessMode = dparameters["headlessMode"]
todownload = dparameters["todownload"]
sleeptime = dparameters["sleeptime"]
usemarionette = dparameters["usemarionette"]
# for selenium to work properly, geckodriver is needed to be downloaded,
# placed in some directory and in next line starting with
# os.environ that directory should be inserted
# geckodriver can be downloaded from
# https://github.com/mozilla/geckodriver/releases
os.environ["PATH"] += ":/data/Scrape"
timeout = 10 # timeout for openning web page
if headlessMode:
display = Display(visible=0, size=(1024, 768))
display.start()
# if log file become large, you can change filemode='w' for logging only individual sessons
logging.basicConfig(filename=dir_in + 'get_FAClog.txt', filemode='a', level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
logging.debug('Started')
time1 = time.time()
ddestdir = {}
ddestdiropp = {}
def is_download_completed():
time.sleep(sleeptime)
l = glob.glob(dir_downloads + '*.crdownload')
while True:
l = glob.glob(dir_downloads + '*.crdownload')
if len(l) == 0:
# print'Downloading ' + audit + ' completed')
break
else:
time.sleep(sleeptime)
def download():
''' function for downloading zip files from server'''
def open_tag(css_selector):
driver.find_element_by_css_selector(css_selector).click()
def enter_in_tag(css_selector, date_string):
driver.find_element_by_css_selector(css_selector).send_keys(date_string)
global url
global rangefrom
global rangeto
url = url.strip()
rangefrom = rangefrom.strip()
rangeto = rangeto.strip()
options = webdriver.ChromeOptions()
options.add_argument("--start-maximized")
prefs = {"download.default_directory" : dir_downloads}
options.add_experimental_option("prefs",prefs)
#profile = webdriver.FirefoxProfile()
#profile.set_preference("browser.download.folderList", 2)
#profile.set_preference("browser.download.manager.showWhenStarting", False)
#profile.set_preference("browser.helperApps.alwaysAsk.force", False)
#profile.set_preference("browser.download.dir", dir_downloads)
#profile.set_preference("browser.helperApps.neverAsk.saveToDisk", "application/zip")
capabilities = DesiredCapabilities.CHROME
#capabilities = DesiredCapabilities.FIREFOX
if usemarionette:
capabilities["marionette"] = True
driver = webdriver.Chrome(chrome_options=options)
#driver = webdriver.Firefox(firefox_profile=profile, capabilities=capabilities)
driver.implicitly_wait(timeout)
print('loading: ' + url)
try:
driver.get(url)
except Exception as e:
logging.debug(str(e))
print(str(e))
sys.exit()
st = html.unescape(driver.page_source)
open_tag('#ui-id-1') # click on GENERAL INFORMATION
time.sleep(0.5)
# unselect All Years
open_tag('#MainContent_UcSearchFilters_FYear_CheckableItems_0')
# click on 2016
open_tag('#MainContent_UcSearchFilters_FYear_CheckableItems_1')
# click on 2017
open_tag('#MainContent_UcSearchFilters_FYear_CheckableItems_2')
# Fill ranges
enter_in_tag('#MainContent_UcSearchFilters_DateProcessedControl_FromDate', rangefrom) #rangefrom
enter_in_tag('#MainContent_UcSearchFilters_DateProcessedControl_ToDate', rangeto) #rangeto
print(rangefrom + ' ' + rangeto)
# click on Search button
open_tag('#MainContent_UcSearchFilters_btnSearch_top')
# click through new PII and Native Tribe information disclosure screen added April 2017
open_tag("#chkAgree")
open_tag("#btnIAgree")
# give info how many results are found
num_of_results = driver.find_element_by_css_selector('.resultsText').text
print(num_of_results + ' RECORD(S)')
logging.debug(num_of_results + ' RECORD(S)')
try:
inum_of_results = int(num_of_results)
bnum = True
if inum_of_results == 0:
logging.info("0 results are found")
print("0 results are found")
bnum = False
except:
logging.critical("num_of_results is not produced")
print("num_of_results is not produced")
bnum = False
# examine Selected Audit Reports
audit_reports_select = Select(driver.find_element_by_css_selector('#MainContent_ucA133SearchResults_ddlAvailZipTop'))
audit_reports_innerHTML = driver.find_element_by_css_selector('#MainContent_ucA133SearchResults_ddlAvailZipTop').get_attribute("innerHTML")
innersoup = BeautifulSoup(audit_reports_innerHTML, "html.parser")
laudit_tags = innersoup.findAll("option")
laudit = []
for option in laudit_tags:
if option["value"].startswith("Audit Reports"):
laudit.append(option["value"])
if len(laudit) == 0:
logging.critical("audit reports list is not produced")
print("audit reports list is not produced")
bnum = False
def is_download_completed():
time.sleep(dparameters["sleeptime"])
l = glob.glob(dir_downloads + '*.part')
zipfilename = ntpath.basename(l[0]).replace('.part', '')
while True:
l = glob.glob(dir_downloads + '*.part')
if len(l) == 0:
# print'Downloading ' + audit + ' completed')
shutil.copy2(dir_downloads + zipfilename, dir_zipmem + zipfilename)
break
else:
time.sleep(dparameters["sleeptime"])
if bnum:
# in this for loop we are selecting by groups of 100
for audit in laudit:
audit_reports_select.select_by_visible_text(audit)
# now we click on Download Audits button
open_tag('#MainContent_ucA133SearchResults_btnDownloadZipTop')
print('Downloading ' + audit)
is_download_completed()
driver.close()
if headlessMode:
display.stop()
def ftp_upload_pdfs():
''' function for uploading pdf files to FTP server '''
# get a list of pdf files in dir_pdfs
lpdfs = glob.glob(dir_pdfs + "*.pdf")
lpdfs.sort()
os.chdir(dir_pdfs) # needed for ftp.storbinary('STOR command work not with paths but with filenames
# connect to FTP server and upload files
try:
ftp = FTP()
# ftp = FTP_TLS()
ftp.connect(dparameters["server"].strip(), dparameters["port"])
ftp.login(user = dparameters["username"].strip(), passwd = dparameters["password"].strip())
# ftp.prot_p() if using FTP_TLS uncomment this line
print("Connection to ftp successfully established...")
for pdffile in lpdfs:
rpdffile = ntpath.basename(pdffile)
try:
destinationdir = ddestdir[ddestdiropp[rpdffile]]
ftp.cwd('/' + destinationdir)
logging.info('upload->/' + destinationdir + '/' + rpdffile)
print('upload->/' + destinationdir + '/' + rpdffile)
except:
logging.info('upload->/' + 'Unclassified' + '/' + rpdffile)
print('upload->/' + 'Unclassified' + '/' + rpdffile)
ftp.cwd('/Unclassified')
ffile = open(pdffile, 'rb')
ftp.storbinary('STOR ' + rpdffile, ffile, 32768)
ffile.close()
# file uploaded delete it now
os.remove(pdffile)
ftp.quit()
except Exception as e:
print(str(e))
logging.critical(str(e))
def remove_non_ascii(text):
return ''.join([i if ord(i) < 128 else ' ' for i in text])
def extract_and_rename():
''' function for extracting zip files and renaming pdf files'''
lloc = glob.glob(dir_downloads + '*.zip')
lloc.sort()
if len(lloc) == 0:
print('no zip file(s). quiting')
logging.info('no zip file(s). quiting')
print('Making connections with ' + dir_in + fileshortnames.strip())
# placing shortnames in dictionary
wbShort = openpyxl.load_workbook(dir_in + fileshortnames.strip(), data_only=True)
sheetShort = wbShort.get_sheet_by_name(sheetShortName.strip())
dshort = {}
row = 2
scrolldown = True
while scrolldown:
dshort[sheetShort['A' + str(row)].value.strip()] = sheetShort['F' + str(row)].value.strip()
ddestdir[sheetShort['A' + str(row)].value.strip()] = sheetShort['G' + str(row)].value.strip()
row += 1
if sheetShort['A' + str(row)].value == None:
scrolldown = False # when finding empty row parsing of Shortnames xlsx will stop
#with open(dir_in + 'json_ftpdir_connections.txt', 'w') as fdump:
# json.dump(ddestdir, fdump)
print('Extracting files..')
for myzipfile in lloc:
with zipfile.ZipFile(myzipfile, "r") as z:
z.extractall(dir_pdfs)
# here comes part for renaming
print('Renaming files..')
print('connecting with FileNameCrossReferenceList.xlsx')
wbCross = openpyxl.load_workbook(dir_pdfs + 'FileNameCrossReferenceList.xlsx', data_only=True)
sheetCross = wbCross.get_sheet_by_name('Table1')
for zrow in range(99):
row = zrow + 2
if sheetCross['A' + str(row)].value == None:
break
lfilename = sheetCross['B' + str(row)].value.strip()
lauditeename = sheetCross['C' + str(row)].value.strip()
lstate = sheetCross['E' + str(row)].value.strip()
lein = sheetCross['F' + str(row)].value.strip()
lyearending = sheetCross['G' + str(row)].value.split('/')[-1].strip()
# try to find short output name
# in case there is in lshortname will be appended shortened name else original auditee name
lname = dshort.get(sheetCross['F' + str(row)].value.strip(), sheetCross['C' + str(row)].value.strip())
# filterling lname from special characters
lname = remove_non_ascii(lname) # this function will replace non ascii characters with single space
lname = lname.replace('/', '_')
lname = lname.replace(':', '_')
lname = lname.replace('\\', '')
#lname = lname.replace("'", "_")
#lname = lname.replace('"', '_')
#lname = lname.replace(',', '')
#lname = lname.replace('&', '')
#lname = lname.replace('.', '')
#lname = lname.replace('#', '')
#lname = lname.replace('%', '')
#lname = lname.replace('{', '')
#lname = lname.replace('}', '')
#lname = lname.replace('<', '')
#lname = lname.replace('>', '')
#lname = lname.replace('*', '')
#lname = lname.replace('?', '')
#lname = lname.replace('$', '')
#lname = lname.replace('!', '')
#lname = lname.replace('@', '')
#lname = lname.replace('+', '')
#lname = lname.replace('`', '')
#lname = lname.replace('|', '')
#lname = lname.replace('=', '')
try:
os.rename(dir_pdfs + lfilename + '.pdf', dir_pdfs + lstate + ' ' + lname + ' ' + lyearending + '.pdf')
ddestdiropp[lstate + ' ' + lname + ' ' + lyearending + '.pdf'] = lein
time.sleep(0.3)
except Exception as e:
print(str(e))
logging.debug(str(e))
print((lfilename + '.pdf').ljust(20) + lstate + ' ' + lname + ' ' + lyearending + '.pdf')
logging.info((lfilename + '.pdf').ljust(20) + lstate + ' ' + lname + ' ' + lyearending + '.pdf')
##### upload to Azure before uploading to pdf
upload_to_file_storage()
#####
ftp_upload_pdfs()
os.remove(myzipfile)
def calculate_time():
time2 = time.time()
hours = int((time2-time1)/3600)
minutes = int((time2-time1 - hours * 3600)/60)
sec = time2 - time1 - hours * 3600 - minutes * 60
print("processed in %dh:%dm:%ds" % (hours, minutes, sec))
if __name__ == '__main__':
if todownload:
download()
extract_and_rename() # since FileNameCrossReferenceList.xlsx is same for all groups,
# script have to use this grouped approaching, processing them by 100 or less for final group
calculate_time()
print('Done.')
#######
# a function to upload files to Azure services (not tested)
def upload_to_file_storage():
# get a list of pdf files in dir_pdfs
lpdfs = glob.glob(dir_pdfs + "*.pdf")
lpdfs.sort()
#os.chdir(dir_pdfs) # needed for ftp.storbinary('STOR command work not with paths but with filenames
# connect to FTP server and upload files
try:
file_storage_url = dparameters['fs_server'].strip()
file_storage_user = dparameters['fs_username'].strip()
file_storage_pwd = dparameters['fs_password'].strip()
file_storage_share = dparameters['fs_share'].strip()
file_storage_dir = dparameters['fs_directory_prefix'].strip()
file_service = FileService(account_name=self.file_storage_user, account_key=self.file_storage_pwd)
try:
if self.file_service.exists(self.file_storage_share):
print('Connection to Azure file storage successfully established...')
if len(self.file_storage_dir)>0 and not self.file_service.exists(self.file_storage_share, directory_name=self.file_storage_dir):
self.file_service.create_directory(self.file_storage_share, self.file_storage_dir)
print('Created directory:' + self.file_storage_dir)
else:
print('Filaed to connect to Asure file storage, share does not exist: '+ self.file_storage_share)
except Exception as ex:
print('Error connecting to Azure file storage: ', ex)
for pdffile in lpdfs:
rpdffile = ntpath.basename(pdffile)
try:
destinationdir = ddestdir[ddestdiropp[rpdffile]]
except:
destinationdir ='Unclassified'
retries = 0
while retries<3:
try:
path = os.path.join(dir_pdfs, rpdffile)
print('Uploading {}'.format(path))
remote_filename = rpdffile
if not remote_filename:
return
if len(self.file_storage_dir)>0:
directory = self.file_storage_dir+'/'+destinationdir
if not self.file_service.exists(self.file_storage_share,directory_name=directory):
self.file_service.create_directory(self.file_storage_share,directory)
if not self.config.getboolean(self.section, 'overwrite_remote_files', fallback=False):
print('Checking if {}/{} already exists'.format(directory, filename))
if self.file_service.exists(self.file_storage_share,directory_name=directory, file_name=filename):
print('{}/{} already exists'.format(directory, filename))
return
self.file_service.create_file_from_path(
self.file_storage_share,
directory,
filename,
path,
content_settings=ContentSettings(content_type='application/pdf'))
print('{} uploaded'.format(path))
retries =3
except Exception as e:
print('Error uploading to Asure file storage,', str(e))
retries+=1
except Exception as e:
print(str(e))
logging.critical(str(e))
######