def path_examples():
print_header('Path examples')
filepath = "~/pyexample.txt"
# Expand shortcut to an abs path to a home dir
filepath = path.expanduser(filepath)
print(f'Path to pyexample: {filepath}')
# Check if file exists
print(f'Path {filepath} exists: {path.exists(filepath)}')
print(f'Path {filepath} is a file: {path.isfile(filepath)}')
print(f'Path {filepath} is a directory: {path.isdir(filepath)}')
parent_dir = '..'
print(f'Parent dir abs path: {path.abspath(parent_dir)}')
# Print relative path
current_dir = path.realpath(path.normpath(path.curdir))
print(
f'Relative path to {filepath} from {current_dir}: {path.relpath(filepath)}'
)
# Symlinks behaviour
symlink_path = path.expanduser('~/.bashrc')
print(f'Abspath to a symlink {symlink_path}: {path.abspath(symlink_path)}')
print(
f'Realpath to a symlink {symlink_path}: {path.abspath(symlink_path)}')
def file_example(file_path=TEST_FILE_PATH):
print_header('Writing to pyexample.txt in a home directory')
# Open file for writing; create if not exists
f = open(file_path, 'w+')
for i in range(10):
f.write(f'Line number: {i}\n')
f.close()
# Open in an append mode
f = open(file_path, 'a')
for i in range(10):
f.write(f'Line number: {i}\n')
f.close()
# Reading all content
f = open(file_path, 'r')
if f.mode == 'r':
contents = f.read()
print(contents)
f.close()
# Reading line by line
f = open(file_path, 'r')
if f.mode == 'r':
fl = f.readlines()
for line in fl:
print(line.strip())
f.close()
def csv_module_example():
print_header('CSV example')
from pprint import pprint
src_file = f'{os.getcwd()}{os.sep}pysharpen{os.sep}dataengineering{os.sep}ingestion{os.sep}taxi.csv.bz2'
for idx, row in enumerate(iter_records(src_file)):
if idx > 10:
break
pprint(row)
def zipfile_examples():
print_header('zipfile examples')
root_dir, fn = path.split(TEST_FILE_PATH)
zip_path = root_dir + os.sep + 'pyexample2.zip'
with ZipFile(zip_path, 'w') as zf:
zf.start_dir
zf.write(TEST_FILE_PATH)
zf.write(root_dir + os.sep + fn + '.bak')
def file_attributes_example():
print_header(header='File attributes examples')
p = path.realpath(path.expanduser('~/pyexample.txt'))
# Get modification time in seconds from Epoch, convert it to string
t = time.ctime(path.getmtime(p))
print(f'Modification time (ctime): {t}')
t = datetime.datetime.fromtimestamp(path.getmtime(p))
print(f'Modification time (datetime.fromtimestamp): {t}')
def html_parsing_examples():
print_header('HTML parsing examples')
cwd = os.getcwd()
filepath = f'{cwd}{os.sep}pysharpen{os.sep}internet{os.sep}samplehtml.html'
with open(filepath, 'r') as f:
if f.mode == 'r':
contents = f.read()
my_parser = MyHTMLParser()
my_parser.feed(contents)
def json_examples():
print_header('JSON examples')
url = 'https://earthquake.usgs.gov/earthquakes/feed/v1.0/summary/2.5_day.geojson'
resp = req.urlopen(url)
if resp.getcode() == 200:
data = resp.read()
print_results(data)
else:
print(f'Something went wrong. Status code: {resp.getcode()}')
def timedelta_examples():
print_header('Timedelta examples')
from datetime import timedelta, datetime
td = timedelta(days=365, hours=10, minutes=2)
print(f'Timedelta 365 days {td}')
now = datetime.now()
year_from_now = now + timedelta(days=365)
print(f'Year from now {year_from_now}')
print(f'In 3 weeks and 2 days it will be {now + timedelta(weeks=3, days=2)}')
def pandas_example():
print_header('Pandas example')
from pprint import pprint
src_file = f'{os.getcwd()}{os.sep}pysharpen{os.sep}dataengineering{os.sep}ingestion{os.sep}taxi.csv.bz2'
with bz2.open(src_file, 'rt') as f:
df = pd.read_csv(f, parse_dates=['tpep_pickup_datetime', 'tpep_dropoff_datetime'])
for idx, row in df.iterrows():
if idx > 10:
break
pprint(row)
def xml_parsing_examples():
print_header('XML parsing examples')
filepath = f'{os.getcwd()}{os.sep}pysharpen{os.sep}internet{os.sep}samplexml.xml'
doc = xml.dom.minidom.parse(filepath)
print(f'First node name: {doc.nodeName}')
print(f'First child tag name: {doc.firstChild.tagName}')
skills = doc.getElementsByTagName('skill')
for skill in skills:
print(f'Has skill: {skill.getAttribute("name")}')
new_skill = doc.createElement('skill')
new_skill.setAttribute('name', 'Microsoft Azure')
doc.firstChild.appendChild(new_skill)
def datetime_examples():
print_header('Datetime examples')
# Get current date and time
datetime = dt.datetime
now = datetime.now()
print(f'Now is: {now}')
time_now = datetime.time(now)
print(f'Time now is: {time_now}')
# Format using strftime function
# %Y - year, %m - month (1-12), %d - day of month(1-31)
# %b - short month abbreviation (Jan-Dec), %B - full month name
# %c - locale's date and time, %x - locale's date, %X - locale's time
# %a - abbreviated day name, %A - full day name
# %I/%H - 12/24 hour format, %M - minute, %S - second, %p - locale's AM/PM format
print("Today using locale's date and time format", now.strftime('%c'))
print("Time using 12 hour and AM/PM format", now.strftime('%I %p'))
def date_examples():
print_header('Date examples')
# Print today's date
date = dt.date
today = date.today()
print(f'Today is: {today}')
# Print date components: year, month, day of month
print(f'Year: {today.year}, month: {today.month}, day: {today.day}')
# Print weekday where 0==Monday, 6==Sunday
print(f'Weekday is: {today.weekday()}')
# Format using strftime function
# %Y - year, %m - month (1-12), %d - day of month(1-31)
# %b - short month abbreviation (Jan-Dec), %B - full month name
# %c - locale's date and time, %x - locale's date, %X - locale's time
# %a - abbreviated day name, %A - full day name
print('Today using dd-mm-yyyy format', today.strftime('%d-%m-%Y'))
print("Today using locale's date format", today.strftime('%x'))
def shell_examples():
print_header('Shell examples')
src = TEST_FILE_PATH
dst = TEST_FILE_PATH + '.bak'
dst1 = TEST_FILE_PATH + '.bak1'
# Copy file
shutil.copy(src, dst)
#Copy all file attributes
shutil.copystat(src, dst)
# Rename file
root_dir, name = path.split(src)
# new_name = root_dir + '/pyexample_new.txt'
# if path.exists(new_name):
# os.remove(new_name)
# os.rename(src, new_name)
# Make zip archive
make_archive(base_name='pytestarch',
format='zip',
root_dir=root_dir,
base_dir=path.realpath(path.expanduser('~/Documents')))
def http_examples():
print_header('HTTP examples')
web_url = req.urlopen('https://google.com')
print(f'Response code: {web_url.getcode()}')
print(f'Response data: {web_url.read()}')
