def test():
page = r"C:\Yahia\Home\Yahia-Dev\Python\training\pdf\data\ABH pages\ABH-025.png"
outfile = f".\\out\\{os.path.split(page)[1].split('.')[0]}.txt"
f = open(outfile, "w", encoding='utf-8')
# filename = "page_"+str(i)+".jpg"
filename = f'.\\data\\ABH pages\\{page}'
# text = str(((pytesseract.image_to_string(Image.open(filename), lang='ara'))))
words= str(((pytesseract.image_to_string(Image.open(page), lang='ara'))))
# print(words)
f.write(words)
f.write ('----------------------------\n')
for w in words.split():
f.write(w + "\n")
f.close()
conn, cursor = open_db()
# print(words)
for w in words.split():
# print (w)
insert_row_list(conn, cursor, 'pdf_dict', [w,w], ignoreUnique=True)
conn.commit()
close_db(cursor)
def load_ACH_folder():
# clear_tk()
data_folder = filedialog.askdirectory(initialdir=".",
title="select data folder",
mustexist=True)
if not data_folder:
return # no files selected
# data_folder = r"C:\Yahia\Python\src\HDB\training\xml\ACH\tttt"
_, cursor = open_db()
if table_exists("GrpHdr", cursor) > 0:
exec_db_cmd('delete from GrpHdr')
# exec_db_cmd('delete from trx')
if table_exists("pacs_008_001_01", cursor) > 0:
exec_db_cmd('delete from pacs_008_001_01')
if table_exists("pacs_002_001_02", cursor) > 0:
exec_db_cmd('delete from pacs_002_001_02')
if table_exists("pacs_004_001_01", cursor) > 0:
exec_db_cmd('delete from pacs_004_001_01')
close_db(cursor)
for folder, subs, files in os.walk(data_folder):
for f in files:
filename, file_extension = os.path.splitext(f)
if file_extension.upper() != ".XML":
continue
xml_to_sqlite(os.path.join(os.path.join(folder, f)))
def xml_to_sqlite(file_name):
print(file_name)
tree = ET.parse(file_name)
root = tree.getroot()
# f = open (".\\out\\parse_xml.txt", 'w', encoding = "UTF8")
conn, cursor = open_db()
for i, L0 in enumerate(root):
# f.writelines (f"====== L0: {local_name(L0.tag)} {len(L0)} ===============\n")
print(f"{i} - len(L0): {len(L0)}, {local_name(L0.tag)}")
for L1 in L0:
L1_rec = dict_to_1L_dict(xml_to_dict(L1))
if L1_rec:
if local_name(L1.tag) == "GrpHdr":
table_name = 'GrpHdr'
MsgId = L1_rec.get('GrpHdr_MsgId')
rec = {
'pacsId': local_name(root[0].tag),
"filename": file_name
}
rec.update(L1_rec)
insert_db_rec(conn, cursor, rec, table_name)
else:
table_name = local_name(L0.tag).replace('.', '_')
L1_rec.update({'MsgId': MsgId})
insert_db_rec(conn, cursor, L1_rec, table_name)
conn.commit()
# f.writelines (f"L1: {local_name(L1.tag)}, {len(L1)}, {20* '-'}, \n, {json.dumps(L1_rec, indent=4)}\n")
close_db(cursor)
def attendees_last_2_month(file_name):
#update_meetings()
sql = f"""SELECT meeting_date, COUNT(name), COUNT(firstname), COUNT(name) - COUNT(firstname)
FROM (
SELECT DATE(join_time) as meeting_date, type as meeting_type, topic, name, firstname
FROM attendees a
LEFT Join students ON a.user_email = students.email
LEFT Join meetings m ON a.meeting_uuid = m.uuid
WHERE DATE(join_time) > DATE('now', '-2 Month')
GROUP BY meeting_date, name
)
GROUP BY meeting_date
ORDER BY 1"""
comm, curspr = open_db()
rows = exec_query(curspr, sql)
close_db(curspr)
bars1 = []
bars2 = []
names = []
# plot last n lines
for row in rows:
names.append(row[0]) # meeting date
bars1.append(row[1]) # count (first name) --> Academy students
bars2.append(row[3]) # External Students
plot_stacked_bar(bars1, bars2, names, file_name)
def load_ACH():
# clear_tk()
# file_path = filedialog.askopenfilename(title="Select file",multiple=False,
# filetypes=(("Excel files", "*,xlsx"), ("Excel files", "*.xlsx")))
# if not file_path:
# return # no files selected
# file_name = r"C:\Yahia\HDB\HDB-CBP\3- Execution\Interfaces\IRDs\ACH\0002\booking\ACH sample\29_4003076817_BOOKING_8034_1.xml"
# file_name = r"C:\Yahia\Home\Yahia-Dev\Python\training\xml\ACH\29_PACS008_2021080309241818109.XML"
# file_name = r"C:\Yahia\Home\Yahia-Dev\Python\training\xml\ACH\29_PACS008_2021080309241818109.XML"
file_name = r"C:\Yahia\Home\Yahia-Dev\Python\training\xml\ACH\tttt\29_PACS008_2021080811485962830.XML"
data_folder = r"C:\Yahia\Home\Yahia-Dev\Python\training\xml\ACH"
fexception = open (r".\out\exceptions.txt", "wt", encoding = "UTF8")
conn, cursor = open_db()
exec_db_cmd('delete from GrpHdr')
exec_db_cmd('delete from trx')
exec_db_cmd('delete from pacs_002_004')
if True:
parse_pacs_file(file_name, conn, cursor, fexception)
else:
for folder, subs, files in os.walk(data_folder):
for f in files:
filename, file_extension = os.path.splitext(f)
if file_extension.upper() != ".XML":
continue
parse_pacs_file(os.path.join(os.path.join(folder, f)), conn, cursor, fexception)
conn.commit()
close_db(cursor)
fexception.close()
def load_increment_scan_result(file_path, output):
output.insert(END, 'Loadind the files:' + file_path + ' .....\n')
if type(file_path) == str: # is folder?
scan_data = load_scan_dir_csv(file_path, output)
else:
scan_data = load_scan_files(file_path, output)
scan_data = replace_temp_profile_name(scan_data)
ips=[r[IP_ADDRESS_COL] for r in scan_data]
output.insert(END," ------- del_old_vulners ---------------\n")
ip_list = '"' + '","'.join(ips) + '"'
cmd = f"DELETE FROM vulnerability WHERE ipaddress in ({ip_list})"
exec_db_cmd(cmd)
output.insert(END," ---- Inset new scan records \n")
conn, cursor = open_db()
for row in scan_data:
insert_row_vulner(conn, cursor, row)
conn.commit()
close_db(cursor)
# lst = check_new_assets(scan_data) # if new assets in this scan, add to assets table
output.insert(END," Add new stats\n")
if add_new_assets(): # there are new assets. stop here and continue after fixing new assets's data
messagebox.showinfo("Warning", "Newly added assets to assets with profile_group '?', please arrange to adjust and then run menu 'Update Stats'" )
return
# add_new_profile_stats() # append stats with newly added profiles
output.insert(END," Update Stats \n")
update_stats(output) # update 'current_' fields with the new stats
def attendees_per_day_of_week(file_name):
#update_meetings()
sql = f"""SELECT strftime('%w',meeting_date) as day_of_week, COUNT(name), COUNT(firstname), COUNT(name) - COUNT(firstname)
FROM (
SELECT DATE(join_time) as meeting_date, name, firstname
FROM attendees a
LEFT Join students ON a.user_email = students.email
LEFT Join meetings m ON a.meeting_uuid = m.uuid
GROUP BY meeting_date, name
)
GROUP BY day_of_week
ORDER BY 1"""
comm, curspr = open_db()
rows = exec_query(curspr, sql)
close_db(curspr)
bars1 = []
bars2 = []
names = [
'Sunday', 'Monday', 'Tuesday', 'Wednesday ', 'Thursday', 'Friday',
'Saturday'
]
# plot last n lines
for row in rows:
#names.append(row[0]) # meeting day
bars1.append(row[1]) # count (first name) --> Academy students
bars2.append(row[3]) # External Students
plot_stacked_bar(bars1, bars2, names, file_name)
def check_new_assets(scan_data): # not used anymore
conn, cursor = open_db()
for row in scan_data:
ip = row[IP_ADDRESS_COL]
cmd = f"SELECT profile_name FROM assets WHERE ipaddress = '{ip}'"
header, lst = query_to_list(cmd)
if len(lst)== 0: # IP not found, add it as is until manual fix, add "(NEW)"
print(f"Newly added server: {ip}, tmp profile:{row[0]}")
new_servers = True
profile_name = row[0]
profile_list.append(profile_name)
rec = [ip, profile_name, row[ASSET_NAME_COL], "?", "?", ""]
try:
insert_row_list(conn, cursor, "assets", rec)
conn.commit()
except:
print (f"check_new_assets: record already exist")
continue # record already exist frrom previous scan row
else: # found, relace temp scan profile name with asset profile_name
profile_list.append(lst[0][0])
close_db(cursor)
if new_servers:
messagebox.showinfo("Warning", "Newly added assets to assets name '(NEW)', please arrange to adjust")
return profile_list
def load_zoom_meetings(from_dt, to_date=""):
conn, cursor = open_db()
create_tables(cursor) # create tables if not exist
meeting_report_url = f"https://api.zoom.us/v2/report/users/{config.get('USER_ID')}/meetings?from={from_dt}&to={to_date}?page_size=300"
headers = {"Authorization": "Bearer " + config.get("JWT_TOKEN")}
r = requests.get(meeting_report_url, headers=headers)
meetings = json.loads(r.content)
if meetings.get("code") == 124:
print(meetings.get("message")) # error
return
page_count = meetings.get('page_count')
page_size = meetings.get('page_size')
total_records = meetings.get('total_records')
for key, value in meetings.items():
if key == 'meetings':
for m in value:
# print (m)
print(f"meeting-id: {m.get('id')}, "
f"type: {m.get('type')}, "
f"topic: {m.get('topic')}, "
f"start time: {m.get('start_time')}, "
f"No of Participants: {m.get('participants_count')}")
if insert_row_meeting(conn, cursor, m) == -1:
print("meeting already loaded, skip it ...")
continue # meeting already exist, skip it
for k, v in m.items():
if k == "uuid": ## meeting id
load_meeting_participants(v, None, conn, cursor)
pass
close_db(cursor)
def get_page_dict(page_no):
conn, cursor = open_db()
rows = exec_query (cursor, f"SELECT * FROM pdf_book WHERE page_no = {page_no}")
close_db(cursor)
# print (page_no, len (rows[0]))
if len(rows) == 0:
return None
else:
return rows
def load_book():
page_path = r"C:\Yahia\Home\Yahia-Dev\Python\training\pdf\data\books\ABH\pages"
conn, cursor = open_db()
for page_no in range (3,75):
page = os.path.join(page_path, f"ABH-{format(page_no, '03')}.png")
print (page_no)
words= str(((pytesseract.image_to_string(Image.open(page), lang='ara'))))
for w in words.split():
insert_row_list(conn, cursor, 'pdf_book', [w,w, page_no,None])
conn.commit()
close_db(cursor)
def query_to_excel(cmd, file_name, header=None):
conn, cursor = open_db()
rows = exec_query(cursor, cmd)
close_db(cursor)
if not header:
header = get_col_names(conn, cmd)
wb = Workbook()
ws = wb.active
ws.append(header)
for row in rows:
ws.append(row)
wb.save(file_name)
def rebuild_page_text(page_no):
conn, cursor = open_db()
rows = exec_query (cursor, f"SELECT page_raw FROM page_text WHERE page_no = {page_no}")
if len(rows) == 0:
tk.messagebox ('Page not found')
close_db(cursor)
return
else:
edited_page = edit_page_text_details(rows[0][0], cursor, page_no)
cmd = f"UPDATE page_text SET page_edited_txt = '{edited_page}' WHERE page_no = {page_no}"
r= exec_db_cmd_conn (cmd, cursor)
if r == 0: #success
update_dict(page_no, conn, cursor)
conn.commit()
close_db(cursor)
return edited_page
def load_db(data_folder, output):
if os.path.isdir(data_folder):
# output.delete(0.0, END) # clear window
output.insert(END, f'Loadind the files: {data_folder}\n')
else:
output.insert(END, f'Data folder does not exist: {data_folder}\n')
return
conn, cursor = open_db()
create_tables(cursor)
for folder, subs, files in os.walk(data_folder):
if folder.split('\\')[-1] == 'old':
output.insert(
END, "*** skip folder ***: " + folder.split('\\')[-2] + "-->" +
folder.split('\\')[-1] + "-->old")
continue
for f in files:
filename, file_extension = os.path.splitext(f)
if file_extension != ".csv":
continue
# print(folder.split('\\')[-2], ",", folder.split('\\')[-1], ",", filename)
output.insert(END, folder.split('\\')[-1] + "-->" + f + '\n')
with open(os.path.join(os.path.join(folder, f))) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
for row in csv_reader:
if len(row) != 28:
output.insert(
END,
f'filename skipped, # col are not 28, it is: {len(row)}" \n'
)
break
if row[0] != 'name': # skip header
# output.insert(END, filename + str(i) + '\n')
insert_row_vulner(conn, cursor, row)
conn.commit()
exec_db_cmd(
"delete from vulnerability WHERE ipaddress = '172.17.90.200' AND name = 'HQ-VLAN-90-Windows-Server-FULL'"
)
close_db(cursor)
insert_base_stats(output)
def stats_attendees_graph():
sql = f"""SELECT meeting_date, meeting_type, topic, COUNT(name), COUNT(firstname), COUNT(name) - COUNT(firstname)
FROM (
SELECT DATE(join_time) as meeting_date, type as meeting_type, topic, name, firstname
FROM attendees a
LEFT Join students ON a.user_email = students.email
LEFT Join meetings m ON a.meeting_uuid = m.uuid
GROUP BY meeting_date, name
)
GROUP BY meeting_date
ORDER BY 1, 2, 3"""
comm, curspr = open_db()
rows = exec_query(curspr, sql)
close_db(curspr)
bars1 = []
bars2 = []
names = []
for row in rows:
names.append(row[0])
bars1.append(row[4])
bars2.append(row[5])
plot_stacked_bar(bars1, bars2, names, r".\data\attendess by date.png")
def pdf2db(page_no):
page = f".\\data\\books\\ABH\\pages\\ABH-{format(page_no, '03')}.png"
words= str(((pytesseract.image_to_string(Image.open(page), lang='ara'))))
# get last record number in dict
conn, cursor = open_db()
rows = exec_query (cursor, "select count(*) FROM pdf_dict")
if len(rows) == 0:
st_dict_no = 1
else:
st_dict_no = rows[0][0]+1
for w in words.split():
insert_row_list(conn, cursor, 'pdf_dict', [w,w,page_no], ignoreUnique=True)
conn.commit()
close_db(cursor)
words = words.replace("'", "*") # replace single quote
words = words.replace('"', "*") # replace double quote
cmd = f"""INSERT INTO page_text VALUES ({page_no}, '{words}', '', {st_dict_no})"""
exec_db_cmd(cmd)