def get_energies_from_files(self):
log.d('Getting energies from files.')
energies_dict = {}
for folder_name in FOLDER_NAMES:
temp_file_list = [
file for file in os.listdir(folder_name)
if file.endswith('.log')
]
for molecule_name in temp_file_list:
text = None
temp_dict = {}
with open(folder_name + '/' + molecule_name, 'r') as f:
text = f.read()
if folder_name in ['1-DFTmin_opt', '2-MP2min_sp']:
energy_value = round(float(DFT_RE.findall(text)[-1]), 5)
temp_dict[folder_name] = energy_value
elif folder_name in ['3-M062Xmin_opt', '4-M062Xmax_sp']:
energy_value = round(float(M06_RE.findall(text)[-1]), 5)
temp_dict[folder_name] = energy_value
if molecule_name[:-4] not in energies_dict:
energies_dict[molecule_name[:-4]] = [temp_dict]
else:
energies_dict[molecule_name[:-4]].append(temp_dict)
log.i(f'Energies from {len(energies_dict.keys())} files recovered.')
# pp.pprint(energies_dict)
return energies_dict
def myMain():
x=input('Enter x:')
if argv[1] == 'zen':
log.level('info')
log.d('debug')
log.i('info x={}'.format(x))
log.w('warn')
log.e('error')
log.c('critical')
else:
if argv[1] == 'basic':
# see Python Docs logging.html 16.6.7. LogRecord attributes
logging.basicConfig(style='{',format="{asctime:s}:{filename:s}:{lineno:d}:{msg:s}",level='DEBUG')
logging.debug('our debug message x={}'.format(x))
logging.warn('our warn message x={}'.format(x))
else:
print("If we don't want to type logging.debug() etc, we have to create our own logger lg=logging.getLogger({})".format(__name__))
lg=logging.getLogger(__name__)
if argv[1]=='easy':
logging.basicConfig(level='INFO')
else:
lg.setLevel('WARN') # optional: defaults to all levels
lg.addHandler(logging.StreamHandler())
lg.handlers[0].setFormatter(logging.Formatter(style='{',fmt="{filename:s}:{funcName:s}():{lineno:d}:{msg:s}"))
lg.debug('our debug mesage')
lg.info('our info here')
def get_web_page(url):
'''
# Let the user know we are trying to download a webpage
# Construct a request with a User-Agent header
# Send the request and read the webpage from the response
# Convert the webpage from bytes to a string, and return it
'''
url = clean_link(url)
log.i('getting: ' + url)
handle = Request(url)
handle.add_header('User-Agent', 'SPD/1.0')
try:
webpage = urlopen(handle).read()
except HTTPError as err:
log.w('a problem occured when getting ' + url)
if err.code == 404:
message = 'the requested page could not be found'
else:
message = 'the server returned a code of ' + str(err.code)
log.w(message)
webpage = str(err.code) # pass the return code as a string
webpage = str(webpage) # convert from bytes to string
log.d(len(webpage))
soup = BeautifulSoup(webpage, 'html.parser')
return soup
def get_web_page(url):
'''
# Let the user know we are trying to download a webpage
# Construct a request with a User-Agent header
# Send the request and read the webpage from the response
# Convert the webpage from bytes to a string, and return it
'''
url = clean_link(url)
log.i('getting: ' + url)
handle = Request(url)
handle.add_header('User-Agent', 'SPD/1.0')
try:
webpage = urlopen(handle).read()
except HTTPError as err:
log.w('a problem occured when getting ' + url)
if err.code == 404:
message = 'the requested page could not be found'
else:
message = 'the server returned a code of ' + str(err.code)
log.w(message)
webpage = str(err.code) # pass the return code as a string
webpage = str(webpage) # convert from bytes to string
log.d(len(webpage))
soup = BeautifulSoup(webpage, 'html.parser')
return soup
def action_download_submitted_images():
global args
# Download all images from the first page
user_submitted = get_submitted_page()
get_all_images(user_submitted)
if args.recursive: # misnomer
while True: # Loop until we can't find a next page link
log.d('looking for next page...')
user_submitted = page_get_next_page(user_submitted)
if user_submitted is None:
log.d('no next page')
break
get_all_images(user_submitted)
def action_download_submitted_images():
global args
# Download all images from the first page
user_submitted = get_submitted_page()
get_all_images(user_submitted)
if args.recursive: # misnomer
while True: # Loop until we can't find a next page link
log.d('looking for next page...')
user_submitted = page_get_next_page(user_submitted)
if user_submitted is None:
log.d('no next page')
break
get_all_images(user_submitted)
def get_energies_from_files(self):
log.d('Getting energies from files.')
energies_dict = {}
folder_names = [
folder for folder in next(os.walk('.'))[1]
if folder[0].isnumeric()
]
folder_names.sort()
for folder_name in folder_names:
try:
temp_file_list = [
file for file in os.listdir(folder_name)
if file.endswith('.log')
]
except FileNotFoundError:
continue
for molecule_name in temp_file_list:
text = None
temp_dict = {}
with open(folder_name + '/' + molecule_name, 'r') as f:
text = f.read()
try:
if 'freq' in folder_name.lower():
free_energ = round(float(FRQ_RE.findall(text)[-1]), 8)
enthalp = round(float(ENT_RE.findall(text)[-1]), 8)
energy_value = 'Free Energy: ' + str(
free_energ) + '\nEnthalpy: ' + str(enthalp)
temp_dict[folder_name] = energy_value
elif len([
method
for method in ['dft', 'mp2min', 'm06', 'b3lyp']
if method in folder_name.lower()
]) > 0:
energy_value = round(float(DFT_RE.findall(text)[-1]),
8)
temp_dict[folder_name] = energy_value
if molecule_name[:-4] not in energies_dict:
energies_dict[molecule_name[:-4]] = [temp_dict]
else:
energies_dict[molecule_name[:-4]].append(temp_dict)
except IndexError:
log.e(f'Error on \'{folder_name+"/"+molecule_name}\'.')
temp_dict[folder_name] = 'missing value'
log.i(f'Energies from {len(energies_dict.keys())} files recovered.')
return energies_dict, folder_names
def page_get_next_page(webpage):
'''
# Find the link to the next page, if it exists
# If it does, download and return the page
# Otherwise, return None explicitly
'''
global args
urls = webpage.find_all('a')
log.d('found %s urls' % len(urls))
log.d(args.next_page_regex.format(args.user_name))
for url in urls:
next_page = re.search(args.next_page_regex.format(args.user_name),
str(url))
if next_page and not next_page == []:
log.d('matches found for %s' % url)
log.d('returning early')
return get_web_page(next_page.expand(r'\1').replace('amp;', ''))
else:
log.d('no matches for %s' % url)
def page_get_next_page(webpage):
'''
# Find the link to the next page, if it exists
# If it does, download and return the page
# Otherwise, return None explicitly
'''
global args
urls = webpage.find_all('a')
log.d('found %s urls' % len(urls))
log.d(args.next_page_regex.format(args.user_name))
for url in urls:
next_page = re.search(
args.next_page_regex.format(args.user_name),
str(url))
if next_page and not next_page == []:
log.d('matches found for %s' % url)
log.d('returning early')
return get_web_page(next_page.expand(r'\1').replace('amp;', ''))
else:
log.d('no matches for %s' % url)
def clean_link(link):
global args
log.d('cleaning link')
old_link = link
if not re.match(r'https?://', link):
link = 'https://' + link
elif 'https://' not in link:
link = link.replace('http://', 'https://')
if args.gifv_as_gif:
link = link.replace('.gifv', '.gif')
if args.webm_as_gif:
link = link.replace('.webm', '.gif')
if '.gfycat.com/' in link: # fix when config
link = link.replace('//zippy.', '//giant.')
link = link.replace('//fat.', '//giant.')
if args.clean_imgur_links:
link = link.replace('?1', '')
if args.imgur_force_grid:
if re.search(r'[a-zA-Z0-9]{7}[bs]\.', link):
link = link.replace('b.', '.')
link = link.replace('s.', '.')
link = link.replace('////', '//')
log.d('%s => %s' % (old_link, link))
return link
def clean_link(link):
global args
log.d('cleaning link')
old_link = link
if not re.match(r'https?://', link):
link = 'https://' + link
elif 'https://' not in link:
link = link.replace('http://', 'https://')
if args.gifv_as_gif:
link = link.replace('.gifv', '.gif')
if args.webm_as_gif:
link = link.replace('.webm', '.gif')
if '.gfycat.com/' in link: # fix when config
link = link.replace('//zippy.', '//giant.')
link = link.replace('//fat.', '//giant.')
if args.clean_imgur_links:
link = link.replace('?1', '')
if args.imgur_force_grid:
if re.search(r'[a-zA-Z0-9]{7}[bs]\.', link):
link = link.replace('b.', '.')
link = link.replace('s.', '.')
link = link.replace('////', '//')
log.d('%s => %s' % (old_link, link))
return link
def download_image(link):
'''
# Let the user know we are trying to download an image at the given link
# Prepare the command (wget) to download the image
# If wget doesn't exist, we raise a FileNotFound error
# Otherwise, if we're on Windows, modify the wget command to avoid an issue
# with GnuWin wget and SSL
# Finally, we run the constructed command to download the image
'''
global args
# --no-check-certificate is used on windows because GnuWin wget fails to
# verify all certificates for some reason
link = clean_link(link)
log.i('downloading: ' + link)
wget_command = [which('wget'), '-b', '-N', '-o', '/dev/null', link]
if (which('wget') is None):
raise WGetNotFoundException('Could not find wget')
elif operating_system() == 'Windows':
log.d('on windows, adjusting wget_command')
wget_command = [
which('wget'), '-b', '-N', '-o', 'NUL', '--no-check-certificate',
link
]
try:
while call(wget_command) != 0:
time.sleep(.05)
log.d('call is not 0')
log.i('retrying...')
except BlockingIOError:
time.sleep(.1)
log.d('BlockingIOError!')
log.w('retrying...')
download_image(link)
def download_image(link):
'''
# Let the user know we are trying to download an image at the given link
# Prepare the command (wget) to download the image
# If wget doesn't exist, we raise a FileNotFound error
# Otherwise, if we're on Windows, modify the wget command to avoid an issue
# with GnuWin wget and SSL
# Finally, we run the constructed command to download the image
'''
global args
# --no-check-certificate is used on windows because GnuWin wget fails to
# verify all certificates for some reason
link = clean_link(link)
log.i('downloading: ' + link)
wget_command = [which('wget'), '-b', '-N', '-o', '/dev/null', link]
if (which('wget') is None):
raise WGetNotFoundException('Could not find wget')
elif operating_system() == 'Windows':
log.d('on windows, adjusting wget_command')
wget_command = [which('wget'), '-b', '-N', '-o', 'NUL',
'--no-check-certificate', link]
try:
while call(wget_command) != 0:
time.sleep(.05)
log.d('call is not 0')
log.i('retrying...')
except BlockingIOError:
time.sleep(.1)
log.d('BlockingIOError!')
log.w('retrying...')
download_image(link)
def download_image_gallery(link):
'''
# Fetch the HTML page at the given link
# If it's a gfycat link, alter the url to point at the gif and download it
# Otherwise, find all '//i.imgur.com' links and download each one
'''
global args
if 'gfycat.com/' in link:
log.d('page is gfycat')
if not re.search(r'\.(gif|webm)', link):
link = link.replace('gfycat', 'fat.gfycat') + '.webm'
download_image(link)
elif 'imgur.com/' in link:
webpage = get_web_page(link)
if str(webpage) == '404' and re.search(r'layout/grid', link):
log.w('grid layout not found, trying again')
webpage = get_web_page(link.replace('/layout/grid', ''))
log.d('page is imgur gallery (limited to first 20 images!)')
urls = webpage.find_all('a')
for url in urls:
if re.search(args.imgur_gallery_image_regex, url.get('href')):
log.d('matched imgur_gallery_image_regex in %s' % url)
download_image(url.get('href'))
else:
log.d('page is imgur grid')
urls = webpage.find_all('img')
for url in urls:
if url.get('data-src'):
if re.search(args.imgur_grid_image_regex,
url.get('data-src')):
log.d('matched data-src in %s, grid image link' % url)
download_image(url.get('data-src'))
elif url.get('src'):
if re.search(args.imgur_gallery_image_regex,
url.get('src')):
log.d('matched src in %s, gallery image link' % url)
download_image(url.get('src'))
else:
log.d('no src, data-src in %s' % url)
def gjf_settings(self):
config_dict = {}
file_list = [file for file in os.listdir() if file.endswith('.pdb')]
if len(file_list) == 0:
log.e(
f'\'.pdb\' files not found in directory \'{os.path.basename(os.getcwd())}\'. Aborting...'
)
quit()
log.i(f'{len(file_list)} files found. Gathering settings...')
while True:
try:
log.d('How many calculations do you wish to perform?')
ncalc = int(input())
log.d(
'Do you want to set number of processors used and memory size available? Default is 8 processors and 1gb of memory. (Y/N) '
)
query = input()
nproc, mem = 8, 1
if query.lower() == 'y':
log.d('How many procesors do you wish to use? ')
nproc = int(input())
log.d('How much memory do you want to use? ')
mem = float(input())
break
except:
log.w('You have not provided a valid input, please try again.')
config_dict['ncalc'] = ncalc
config_dict['nproc'] = nproc
config_dict['mem'] = mem
config_dict['chk'] = 'chkfile.chk'
for calc_number in range(ncalc):
type_list = [
'DFTmin', 'MP2min', 'MP2max', 'M062Xmin', 'M062Xmax', 'Custom'
]
opt_list = [
'Local minimum', 'Transition State', 'Restart from Checkpoint'
]
freq_list = ['Complete', 'no Raman']
method_list = ['B3LYP', 'MP2', 'M062X']
basis_list = ['6-31G(d)', '6-311+G(d,p)']
log.d(
f'For calculation number {calc_number}, choose a calculation type preset by its number or type \'custom\' for custom settings...'
)
for val, name in enumerate(type_list):
print(f'{val:15}) {name}')
calc_type = input()
log.d(
f'For calculation number {calc_number}, do you wish optimization (Y/N):'
)
query = input()
if query.lower() == 'y':
log.d(f'Which optimization type do you wish :')
for val, name in enumerate(opt_list):
print(f'{val:15}) {name}')
opt_type = input()
log.d(
f'For calculation number {calc_number}, do you wish frequency calculations (Y/N):'
)
query = input()
if query.lower() == 'y':
log.d(f'Which frequency calculation do you wish:')
for val, name in enumerate(freq_list):
print(f'{val:15}) {name}')
opt_type = input()
if calc_type.lower() == 'custom':
log.d(
f'For calculation number {calc_number}, select calculation method:'
)
for val, name in enumerate(method_list):
print(f'{val:15}) {name}')
calc_method = input()
log.d(
f'For calculation number {calc_number}, select basis set:')
for val, name in enumerate(basis_list):
print(f'{val:15}) {name}')
basis_set = input()
log.d(
f'For calculation number {calc_number}, do you wish to specify a solvent (Y/N):'
)
query = input()
if query.lower() == 'y':
query_text1 = 'Please input solvent name:'
solvent = input(f'{query_text1:15}')
pp.pprint(config_dict)
return config_dict
def download_image_gallery(link):
'''
# Fetch the HTML page at the given link
# If it's a gfycat link, alter the url to point at the gif and download it
# Otherwise, find all '//i.imgur.com' links and download each one
'''
global args
if 'gfycat.com/' in link:
log.d('page is gfycat')
if not re.search(r'\.(gif|webm)', link):
link = link.replace('gfycat', 'fat.gfycat') + '.webm'
download_image(link)
elif 'imgur.com/' in link:
webpage = get_web_page(link)
if str(webpage) == '404' and re.search(r'layout/grid', link):
log.w('grid layout not found, trying again')
webpage = get_web_page(link.replace('/layout/grid', ''))
log.d('page is imgur gallery (limited to first 20 images!)')
urls = webpage.find_all('a')
for url in urls:
if re.search(args.imgur_gallery_image_regex, url.get('href')):
log.d('matched imgur_gallery_image_regex in %s' % url)
download_image(url.get('href'))
else:
log.d('page is imgur grid')
urls = webpage.find_all('img')
for url in urls:
if url.get('data-src'):
if re.search(args.imgur_grid_image_regex, url.get('data-src')):
log.d('matched data-src in %s, grid image link' % url)
download_image(url.get('data-src'))
elif url.get('src'):
if re.search(args.imgur_gallery_image_regex, url.get('src')):
log.d('matched src in %s, gallery image link' % url)
download_image(url.get('src'))
else:
log.d('no src, data-src in %s' % url)
