def create_individual_pdfs(revue):
path = revue.conf["Paths"]
# Create front pages for individual actors, if they don't already exist:
frontpages_list = []
for actor in revue.actors:
file_name = "forside-{}.pdf".format(actor.name)
if not os.path.isfile(os.path.join(path["pdf cache"], file_name)):
tex = TeX(revue)
tex.create_frontpage(subtitle=actor.name)
frontpages_list.append([tex, file_name])
# Create front pages:
conv = cv.Converter()
conv.parallel_textopdf(frontpages_list, outputdir=path["pdf cache"])
total_list = []
for actor in revue.actors:
individual_list = (os.path.join(path["pdf cache"], "forside-{}.pdf".format(actor.name)),
os.path.join(path["pdf"],"aktoversigt.pdf"),
os.path.join(path["pdf"],"rolleliste.pdf"),
actor,
os.path.join(path["pdf"],"rekvisitliste.pdf"))
total_list.append((individual_list,
os.path.join(path["individual pdf"],
"{}.pdf".format(actor.name))))
pdf = PDF()
pdf.parallel_pdfmerge(total_list)
def create_song_manus_pdf(revue):
path = revue.conf["Paths"]
# Create front page, if it doesn't already exist:
# if not os.path.exists(os.path.join(path["pdf"], "cache")):
# os.mkdir(os.path.join(path["pdf"], "cache"))
# if not os.path.isfile(os.path.join(path["pdf"], "cache", "forside-sangmanuskript.pdf")):
# Det tager vare på sig selv nu
tex = TeX(revue)
tex.create_frontpage(subtitle="sangmanuskript")
tex.topdf("forside-sangmanuskript.pdf",
outputdir=os.path.join(path["pdf"], "cache"))
# Create song manuscript:
file_list = [
os.path.join(path["pdf"], "cache", "forside-sangmanuskript.pdf")
]
for act in revue.acts:
for material in act.materials:
if material.category == path["songs"]:
file_list.append((os.path.join(
path["pdf"],
os.path.dirname(os.path.relpath(material.path)),
"{}.pdf".format(material.file_name[:-4])), material.title))
pdf = PDF()
pdf.pdfmerge(file_list, os.path.join(path["pdf"], "sangmanuskript.pdf"))
class TextToPDF:
def __init__(self, font='JetBrainsMono'):
self.pdf = PDF(font)
self.errors = []
def input_from_file(self, path):
try:
self.pdf.print_chapter(path)
except (FileNotFoundError, PermissionError) as ex:
self.errors.append(f"{path} file does not exist")
def input_from_files(self, paths):
for path in paths:
self.input_from_file(path)
def input_from_package(self, path, extension=".java"):
try:
# files = [path + "/" + file_path for file_path in os.listdir(path) if file_path.endswith(extension)]
files = [path + "/" + file_path for file_path in os.listdir(path)]
self.input_from_files(files)
except FileNotFoundError as ex:
self.errors.append(f"{path} folder does not exist")
def output(self, path):
try:
self.pdf.output(path, 'F')
except FileNotFoundError as ex:
self.errors.append(f"{path} folder does not exist")
def __init__(self, settings):
self.context = None
self.totalCount = 0
self.cfbf = CFBF()
self.pdf = PDF()
self.ooxml = OOXML()
self.xls_result = []
self.ppt_result = []
self.doc_result = []
self.xlsx_result = []
self.pptx_result = []
self.docx_result = []
self.PyPDF_result = []
self.PDFNoModule_result = []
def OnPrintPage( self, page ):
exportGrid = self.prepareGrid( page )
category = self.pageInfo[page][0]
pageNumber = self.pageInfo[page][3]
pageTotal = self.pageInfo[page][4]
fname = u'{fileBase}-{categoryName}.pdf'.format(
fileBase = self.fileBase,
categoryName = category.fullname if category != 'Primes' else 'Primes'
)
fname = Utils.RemoveDisallowedFilenameChars( fname ).replace( ' ', '-' )
if not self.pdf:
self.pdf = PDF( orientation = 'L' if self.orientation == wx.LANDSCAPE else 'P' )
self.pdf.set_font( 'Arial', '', 12 )
self.pdf.set_author( unicode(getpass.getuser()).encode('iso-8859-1','ignore') )
self.pdf.set_keywords( unicode('CrossMgr Results').encode('iso-8859-1','ignore') )
self.pdf.set_creator( unicode(Version.AppVerName).encode('iso-8859-1','ignore') )
self.pdf.set_title( unicode(os.path.splitext(fname)[0].replace('-', ' ')).encode('iso-8859-1','ignore') )
exportGrid.drawToFitPDF( *([self.pdf, self.orientation] + self.pageInfo[page][1:-1]) )
if not self.allInOne and pageNumber == pageTotal:
if self.dir and not os.path.isdir( self.dir ):
os.mkdir( self.dir )
fname = os.path.join( self.dir, fname )
self.pdf.output( fname, 'F' )
self.lastFName = fname
self.pdf = None
return True
def test():
# logging.basicConfig(level=logging.INFO)
query = HKEX_API(from_date=n_yearsago(n=1), to_date=today())
for data in query.data:
try:
url = data.file_link
# url = 'https://www.dropbox.com/'
print(url)
pdf = PDF(url)
pdf_obj = pdf.pdf_obj
f = AuditFee(pdf_obj)
tab_sum = []
for table in f.tables:
tab_sum.append(table.summary)
except KeyboardInterrupt:
break
except Exception as e:
# print(e)
result = {
'table_summary' : e,
'ERROR': True,
'url' : url,
}
write_to_csv(result, 'result_3.csv')
continue
else:
# print('ok')
result = {
'table_summary' : list(filter(None, tab_sum)),
'ERROR': None,
'url' : url
}
write_to_csv(result, 'result_3.csv')
def create_individual_pdfs(revue):
path = revue.conf["Paths"]
## Create front pages for individual actors, if they don't already exist:
# frontpages_list = []
# for actor in revue.actors:
# file_name = "forside-{}.pdf".format(actor.name)
# if not os.path.isfile(os.path.join(path["pdf cache"], file_name)):
# tex = TeX(revue)
# tex.create_frontpage(subtitle=actor.name)
# frontpages_list.append([tex, file_name])
# Det burde ordne sig selv nu:
def tex_for_front_page(name):
tex = TeX(revue)
tex.create_frontpage(subtitle=name)
return tex
frontpages_list = [[
tex_for_front_page(actor.name), "forside-{}.pdf".format(actor.name)
] for actor in revue.actors]
# Create front pages:
conv = cv.Converter()
conv.parallel_textopdf(frontpages_list, outputdir=path["pdf cache"])
total_list = []
for actor in revue.actors:
individual_list = ((os.path.join(path["pdf cache"],
"forside-{}.pdf".format(actor.name)),
"Forside"), (os.path.join(path["pdf"],
"aktoversigt.pdf"),
"Aktoversigt"),
(os.path.join(path["pdf"], "rolleliste.pdf"),
"Rolleliste"), actor,
(os.path.join(path["pdf"],
"kontaktliste.pdf"), "Kontaktliste"))
total_list.append((individual_list,
os.path.join(path["individual pdf"],
"{}.pdf".format(actor.name))))
pdf = PDF()
pdf.parallel_pdfmerge(total_list)
def OnPrintPage(self, page):
exportGrid = self.prepareGrid(page)
try:
category = self.pageInfo[page][0]
except Exception as e:
# Handle case of no data.
return True
pageNumber = self.pageInfo[page][3]
pageTotal = self.pageInfo[page][4]
fname = u'{fileBase}-{categoryName}.pdf'.format(
fileBase=self.fileBase,
categoryName=category.fullname
if category != 'Primes' else 'Primes')
fname = Utils.RemoveDisallowedFilenameChars(fname).replace(' ', '-')
if not self.pdf:
self.pdf = PDF(
orientation='L' if self.orientation == wx.LANDSCAPE else 'P')
self.pdf.set_font('Arial', '', 12)
self.pdf.set_author(
unicode(getpass.getuser()).encode('iso-8859-1', 'ignore'))
self.pdf.set_keywords(
unicode('CrossMgr Results').encode('iso-8859-1', 'ignore'))
self.pdf.set_creator(
unicode(Version.AppVerName).encode('iso-8859-1', 'ignore'))
self.pdf.set_title(
unicode(os.path.splitext(fname)[0].replace('-', ' ')).encode(
'iso-8859-1', 'ignore'))
exportGrid.drawToFitPDF(*([self.pdf, self.orientation] +
self.pageInfo[page][1:-1]))
if not self.allInOne and pageNumber == pageTotal:
if self.dir and not os.path.isdir(self.dir):
os.mkdir(self.dir)
fname = os.path.join(self.dir, fname)
self.pdf.output(fname, 'F')
self.lastFName = fname
self.pdf = None
return True
def create_song_manus_pdf(revue):
path = revue.conf["Paths"]
# Create front page, if it doesn't already exist:
if not os.path.exists(os.path.join(path["pdf"], "cache")):
os.mkdir(os.path.join(path["pdf"], "cache"))
if not os.path.isfile(os.path.join(path["pdf"], "cache", "forside-sangmanuskript.pdf")):
tex = TeX(revue)
tex.create_frontpage(subtitle="sangmanuskript")
tex.topdf("forside-sangmanuskript.pdf", outputdir=os.path.join(path["pdf"], "cache"))
# Create song manuscript:
file_list = [os.path.join(path["pdf"], "cache", "forside-sangmanuskript.pdf")]
for act in revue.acts:
for material in act.materials:
if material.category == path["songs"]:
file_list.append(os.path.join(path["pdf"], path["songs"],
"{}.pdf".format(material.file_name[:-4])))
pdf = PDF()
pdf.pdfmerge(file_list, os.path.join(path["pdf"],"sangmanuskript.pdf"))
def main(config=None, label=None):
# Setup PDF Generator
pdf = PDF("A4")
# Start initial page, always one
pdf.add_page()
# Command run from console with label input
# Generate label and exit
if label:
# Add all fonts here
pdf.add_font("cambria", "", "fonts/cambria.ttf", True)
pdf.add_font("cambria", "B", "fonts/cambria_B.ttf", True)
pdf.generate(**label)
return
if config:
server = Server(config, pdf)
server.run()
def post(self):
title = self.get_argument('title', 'This is the title')
circles = int(self.get_argument('circles', 10))
lines = int(self.get_argument('lines', 10))
pdf = PDF()
pdf.start(title, circles, lines)
pdf.set_title(title)
filename = pdf.save()
self.write(filename)
def print_aso_bib(participant, copies=2):
license_holder = participant.license_holder
copies = int(copies)
pdf = PDF(orientation='P')
pdf.set_subject('Bib number and rider info in aso format.')
pdf.set_keywords(
'RaceDB CrossMgr Bicycle Racing Software Database Road Time Trial MTB CycloCross RFID'
)
for c in xrange(copies):
aso_bib(pdf, participant.bib, license_holder.first_name,
license_holder.last_name, participant.competition.name)
return pdf.output(dest='s')
def print_aso_bib_two_per_page(participant):
pdf = PDF(orientation='P')
pdf.set_subject(
'Bib number and rider info in modified aso format, two per page.')
pdf.set_keywords(
'RaceDB CrossMgr Bicycle Racing Software Database Road Time Trial MTB CycloCross RFID'
)
license_holder = participant.license_holder
aso_bib_two_per_page(pdf, participant.bib, license_holder.first_name,
license_holder.last_name,
participant.competition.name)
return pdf.output(dest='s')
def debug(url, p):
pdf = PDF(url)
pdf_obj = pdf.pdf_obj
f = AuditFee(pdf_obj)
section = f.target_section(p)
print(section.extract_text())
table = AuditFeeTable(section)
# print('curr_idx:', table.currency_idx)
# print("amount_idx:", table.amount_idx)
# print("year_idx", table.year_idx)
# print("co_row_idx:", table.co_row_idx)
# print("co_col_idx:",table.co_col_idx)
# print(table.raw_table)
print(table.table)
print(table.summary)
def process_pdf(input_path, db_feed):
'''
kicks off pdf processing
db_feed - pdf json from db
input_path - path to pdf
'''
# initializing pdf object & set parameters
pdf_object = PDF(db_feed)
# parsing pdf - input path (?)
pdf_content = PDFparser().parse(input_path)
# building dataframe
df = PDFparser().create_df(pdf_content, pdf_object.page_pattern,
pdf_object.table_pattern, pdf_object.column)
# continue df transformation & filtering only if parsing success
if (df is not None):
return process_df(pdf_object, df)
else:
print('no dataframe passed')
def main():
args = parse()
# opciones
pdf = PDF()
pdf.input_title()
if args.clear:
data_clear(pdf)
elif args.cities:
compare_city(args.cities, pdf)
elif args.states:
compare_state(args.states, pdf)
elif args.type:
compare_restaurant(pdf, args.type)
else:
print(
'Error: se requiere uno o mas argumentos para realizar la accion. Pulsa -h para más información'
)
url_pdf = url + "/../pdf/"
pdf.output(url_pdf + "analytic.pdf", 'F')
def print_bib_tag_label(participant,
sponsor_name=None,
left_page=True,
right_page=True,
barcode=True):
competition = participant.competition
license_holder = participant.license_holder
bib = participant.bib
name = license_holder.first_last
if len(name) > 32:
name = license_holder.first_last_short
if sponsor_name is None:
if competition.number_set and competition.number_set.sponsor:
sponsor_name = competition.number_set.sponsor
else:
sponsor_name = competition.name
system_name = 'CrossMgr'
# Use points at the units.
page_width = 3.9 * inches_to_points
page_height = 2.4 * inches_to_points
pdf = PDF('L', (page_height, page_width))
pdf.set_author(RaceDBVersion)
pdf.set_title('Race Bib Number: {}'.format(bib))
pdf.set_subject(
'Bib number and rider info to be printed as a label to apply on the chip tag.'
)
pdf.set_creator(getpass.getuser())
pdf.set_keywords(
'RaceDB CrossMgr Bicycle Racing Software Database Road Time Trial MTB CycloCross RFID'
)
pdf.add_font('din1451alt',
style='',
fname=get_font_file('din1451alt G.ttf'),
uni=True)
pdf.add_font('Arrows',
style='',
fname=get_font_file('Arrrows-Regular.ttf'),
uni=True)
margin = min(page_height, page_width) / 18.0
sep = margin / 2.5
height = page_height - margin * 2.0
width = page_width - margin * 2.0
header = Rect(margin, margin, width, height / 18.0)
footer = Rect(margin, page_height - margin - header.height, header.width,
header.height)
field = Rect(header.x, header.bottom + sep, width,
footer.top - header.bottom - sep * 2)
license_code = license_holder.uci_id or license_holder.license_code
leftArrow, rightArrow = 'A', 'a'
font_name = 'Helvetica'
for lp in ([True] if left_page else []) + ([False] if right_page else []):
pdf.add_page()
arrow = copy.deepcopy(header)
arrow.y -= arrow.height * 0.5
arrow.height *= 2
pdf.set_font('Arrows')
arrowWidth = arrow.draw_text_to_fit(
pdf,
leftArrow if lp else rightArrow,
(Rect.AlignLeft if lp else Rect.AlignRight) | Rect.AlignMiddle,
consider_descenders=True,
convert_to_text=False,
)
arrowWidth += pdf.get_string_width(' ')
header_remain = copy.deepcopy(header)
if lp:
header_remain.x += arrowWidth
header_remain.width -= arrowWidth
pdf.set_font(font_name)
header_remain.draw_text_to_fit(
pdf, sponsor_name,
(Rect.AlignLeft if lp else Rect.AlignRight) | Rect.AlignMiddle,
True)
pdf.set_font('din1451alt', '', 16)
field.draw_text_to_fit(pdf, bib, Rect.AlignCenter | Rect.AlignMiddle)
pdf.set_font(font_name)
name_width = footer.draw_text_to_fit(
pdf, name,
(Rect.AlignRight if lp else Rect.AlignLeft) | Rect.AlignMiddle)
logo = copy.deepcopy(footer)
if not lp:
logo.x += name_width + sep
logo.width -= name_width + sep
if logo.width > 20:
logo_width = logo.draw_text_to_fit(
pdf, system_name,
(Rect.AlignLeft if lp else Rect.AlignRight) | Rect.AlignMiddle)
else:
logo_width = 0
if barcode:
remaining_width = header.width - name_width - logo_width
if lp:
barcode_rect = Rect(footer.x + logo_width, footer.y,
remaining_width, footer.height)
else:
barcode_rect = Rect(
footer.right - logo_width - remaining_width, footer.y,
remaining_width, footer.height)
if license_code:
draw_code128(pdf, license_code, barcode_rect.x, barcode_rect.y,
barcode_rect.width, barcode_rect.height)
pdf_str = pdf.output(dest='s')
return pdf_str
def print_bib_on_rect(bib,
license_code=None,
name=None,
logo=None,
widthInches=5.9,
heightInches=3.9,
copies=1,
onePage=False):
page_width = widthInches * inches_to_points
page_height = heightInches * inches_to_points
pdf = PDF('L', (page_height * (copies if onePage else 1), page_width))
pdf.set_author(RaceDBVersion)
pdf.set_title('Race Bib Number: {}'.format(bib))
pdf.set_subject('Bib number.')
pdf.set_creator(getpass.getuser())
pdf.set_keywords(
'RaceDB CrossMgr Bicycle Racing Software Database Road Time Trial MTB CycloCross RFID'
)
pdf.add_font('din1451alt',
style='',
fname=get_font_file('din1451alt G.ttf'),
uni=True)
margin = min(page_height, page_width) / 17.5
sep = margin / 2.5
height = page_height - margin * 2.0
width = page_width - margin * 2.0
text_margin = margin
text_height = margin * 0.4
for c in xrange(copies):
if c == 0 or not onePage:
pdf.add_page()
page_y = 0
else:
page_y = page_height * c
pdf.dashed_line(0, page_y, page_width, page_y, space_length=12)
pdf.set_font('din1451alt', '', 16)
field = Rect(margin, margin + page_y, width, height)
field.draw_text_to_fit(pdf, bib, Rect.AlignCenter | Rect.AlignMiddle)
pdf.set_font('Helvetica')
if logo:
x = text_margin
logo_rect = Rect(x, page_height - margin + page_y,
(page_width - barcode_width_max) / 2.0 - x,
text_height)
logo_rect.draw_text_to_fit(pdf, logo,
Rect.AlignLeft | Rect.AlignMiddle)
if license_code:
barcode_rect = Rect(margin, page_height - margin * 1.2 + page_y,
width, margin * 0.8)
draw_code128(pdf, license_code, barcode_rect.x, barcode_rect.y,
barcode_rect.width, barcode_rect.height)
if name:
x = (page_width + barcode_width_max) / 2.0
name_rect = Rect(x, page_height - margin + page_y,
page_width - text_margin - x, text_height)
name_rect.draw_text_to_fit(pdf, name,
Rect.AlignRight | Rect.AlignMiddle)
pdf_str = pdf.output(dest='s')
return pdf_str
from pdf import PDF, Word, Document, Html
#function
def show_common(obj):
if type(obj) == PDF:
print(obj.show())
elif type(obj) == Word:
print(obj.show())
elif type(obj) == Html:
obj.print()
elif type(obj) == Document:
print(obj.show())
# print(obj.name() + ' is an abstract class. Cannot say anything!')
docs = [PDF('Doc1'), Word('Doc2'), Document('Doc3'), Html('Doc4')]
for d in docs:
# print(d.show())
show_common(d)
# finds path of files
# making an output directory for pdf merged
output_merge = file_path_variable + '/output_merged'
if not os.path.exists(output_merge):
os.mkdir(output_merge)
for subdir, dirs, files in os.walk(file_path_variable):
for filename in files:
filepath = subdir + os.sep + filename
print(filepath)
ppt = Ex()
if filepath.endswith(".ppt"):
folder = filepath.replace('/', '\\')
ppt.ppt_convert(folder)
if filepath.endswith(".pptx"):
folder = filepath.replace('/', '\\')
ppt.ppt_convert(folder)
if filepath.endswith(".pptm"):
folder = filepath.replace('/', '\\')
ppt.ppt_convert(folder)
pdf = PDF()
pdf.p(file_path_variable, output_merge.replace('/', '\\'))
root.mainloop()
def gen_pdf_quiz(cfg):
for user in cfg:
pdf = PDF()
for i in range(cfg[user]['global']['pages']):
pdf.add_page()
pdf.set_title('四则运算练习')
pdf.set_date(date=cfg[user]['global']['show_date'])
quizzes = bulk_quiz_gen(cfg[user])
pdf.set_quizzes(quizzes=quizzes)
quiz_dir = cfg[user]['global']['quiz_dir']
quiz_dir = os.path.expanduser(quiz_dir)
pdf_filename = os.path.join(quiz_dir,
f'{user}.pdf' if user else 'quizzes.pdf')
pdf.output(f'{pdf_filename}', 'F')
if len(conf.cmd_parts) == 0:
arglist = ("aktoversigt", "roles", "frontpage", "props",
"contacts", "material","individual", "songmanus")
elif "manus" in sys.argv:
arglist = ("aktoversigt", "roles", "frontpage", "props",
"contacts", "material")
else:
arglist = sys.argv[1:]
for arg in arglist:
create_parts(revue, arg)
if len(conf.cmd_parts) == 0 or "manus" in sys.argv:
pdf = PDF()
pdf.pdfmerge((os.path.join(path["pdf"],"forside.pdf"),
os.path.join(path["pdf"],"aktoversigt.pdf"),
os.path.join(path["pdf"],"rolleliste.pdf"),
revue,
os.path.join(path["pdf"],"rekvisitliste.pdf"),
os.path.join(path["pdf"],"kontaktliste.pdf")),
os.path.join(path["pdf"],"manuskript.pdf"))
print("Manuscript successfully created!")
for act in revue.acts:
for material in act.materials:
metadata.update_mod_time(material)
for f in glob.glob(os.path.join(path["pdf"], "*.pdf")):
class CrossMgrPrintoutPDF(CrossMgrPrintout):
def __init__(self,
dir,
fileBase,
orientation,
categories=None,
allInOne=False):
CrossMgrPrintout.__init__(self, categories)
self.dir = dir
self.fileBase = fileBase
self.orientation = orientation
self.allInOne = allInOne
self.pdf = None
self.lastFName = None
def OnEndPrinting(self):
if self.pdf and self.allInOne:
if self.dir and not os.path.isdir(self.dir):
os.mkdir(self.dir)
fname = u'{fileBase}.pdf'.format(fileBase=self.fileBase)
self.pdf.set_title(
unicode(os.path.splitext(fname)[0].replace('-', ' ')).encode(
'iso-8859-1', 'ignore'))
fname = os.path.join(self.dir, fname)
self.pdf.output(fname, 'F')
self.lastFName = fname
self.pdf = None
return super(CrossMgrPrintoutPDF, self).OnEndPrinting()
def OnPrintPage(self, page):
exportGrid = self.prepareGrid(page)
category = self.pageInfo[page][0]
pageNumber = self.pageInfo[page][3]
pageTotal = self.pageInfo[page][4]
fname = u'{fileBase}-{categoryName}.pdf'.format(
fileBase=self.fileBase,
categoryName=category.fullname
if category != 'Primes' else 'Primes')
fname = Utils.RemoveDisallowedFilenameChars(fname).replace(' ', '-')
if not self.pdf:
self.pdf = PDF(
orientation='L' if self.orientation == wx.LANDSCAPE else 'P')
self.pdf.set_font('Arial', '', 12)
self.pdf.set_author(
unicode(getpass.getuser()).encode('iso-8859-1', 'ignore'))
self.pdf.set_keywords(
unicode('CrossMgr Results').encode('iso-8859-1', 'ignore'))
self.pdf.set_creator(
unicode(Version.AppVerName).encode('iso-8859-1', 'ignore'))
self.pdf.set_title(
unicode(os.path.splitext(fname)[0].replace('-', ' ')).encode(
'iso-8859-1', 'ignore'))
exportGrid.drawToFitPDF(*([self.pdf, self.orientation] +
self.pageInfo[page][1:-1]))
if not self.allInOne and pageNumber == pageTotal:
if self.dir and not os.path.isdir(self.dir):
os.mkdir(self.dir)
fname = os.path.join(self.dir, fname)
self.pdf.output(fname, 'F')
self.lastFName = fname
self.pdf = None
return True
def __init__(self, font='JetBrainsMono'):
self.pdf = PDF(font)
self.errors = []
def pdf(request):
pdf = PDF(request.display_user)
return pdf.as_response()
def print_id_label(participant):
competition = participant.competition
license_holder = participant.license_holder
bib = participant.bib
name = license_holder.first_last
if len(name) > 32:
name = license_holder.first_last_short
system_name = 'CrossMgr'
inches_to_points = 72.0
# Use points at the units.
page_width = 3.9 * inches_to_points
page_height = 2.4 * inches_to_points
pdf = PDF('L', (page_height, page_width))
pdf.set_author(RaceDBVersion)
pdf.set_title('Bib Number: {}'.format(bib))
pdf.set_subject('Rider ID and Emergency Information.')
pdf.set_creator(getpass.getuser())
pdf.set_keywords(
'RaceDB CrossMgr Bicycle Racing Software Database Road Time Trial MTB CycloCross'
)
margin = min(page_height, page_width) / 18.0
sep = margin / 2.5
height = page_height - margin * 2.0
width = page_width - margin * 2.0
header = Rect(margin, margin, width, height / 10.0)
footer_height = height / 20
footer = Rect(margin, page_height - margin - footer_height, header.width,
footer_height)
field = Rect(header.x, header.bottom + sep, width,
footer.top - header.bottom - sep * 2)
leftArrow, rightArrow = chr(172), chr(174)
font_name = 'Helvetica'
pdf.add_page()
pdf.set_font(font_name, 'b')
header.draw_text_to_fit(pdf, name, Rect.AlignLeft, True)
pdf.set_font(font_name)
info = []
info.append([
'',
u', '.join([
u'Age: {}'.format(license_holder.get_age()),
u'Gender: {}'.format(license_holder.get_gender_display()),
u'Nation: {}'.format(license_holder.nation_code),
]),
])
info.append(['', ''])
if participant.team:
info.append(['', u'{}'.format(participant.team.name)])
info.append([
'',
u', '.join([
u'Bib: {}'.format(participant.bib),
u'Category: {}'.format(participant.category.code_gender
if participant.category else ''),
]),
])
if license_holder.phone:
info.append([
'',
u' '.join([
u'Phone: {}'.format(format_phone(license_holder.phone)),
]),
])
info.append(['', ''])
if license_holder.emergency_medical:
info.append([
'', u'Medical Alert: {}'.format(license_holder.emergency_medical)
])
info.append(['', u'Emergency Contact:'])
if license_holder.emergency_contact_name:
info.append([
'', u' {}'.format(license_holder.emergency_contact_name
or 'None provided')
])
info.append([
'', u' {}'.format(
format_phone(license_holder.emergency_contact_phone)
or 'No phone number provided')
])
pdf.table_in_rectangle(field.x,
field.y,
field.width,
field.height,
info,
leftJustifyCols=[0, 1],
hasHeader=False,
horizontalLines=False)
footer.draw_text_to_fit(pdf, system_name, Rect.AlignRight, True)
pdf_str = pdf.output(dest='s')
return pdf_str
class DocumentMetadataIngestModule(DataSourceIngestModule):
_logger = Logger.getLogger(DocumentMetadataIngestModuleFactory.moduleName)
def log(self, level, msg):
self._logger.logp(level, self.__class__.__name__,
inspect.stack()[1][3], msg)
def __init__(self, settings):
self.context = None
self.totalCount = 0
self.cfbf = CFBF()
self.pdf = PDF()
self.ooxml = OOXML()
self.xls_result = []
self.ppt_result = []
self.doc_result = []
self.xlsx_result = []
self.pptx_result = []
self.docx_result = []
self.PyPDF_result = []
self.PDFNoModule_result = []
def startUp(self, context):
self.context = context
pass
def getTitles(self, result):
titles = []
for i in result:
for j in i.keys():
if j == "handle":
continue
titles.append(j)
return list(set(titles))
def addData(self, titles, result, filetype, skCase):
for title in titles:
try:
attID = skCase.addArtifactAttributeType(
"TSK_" + filetype + "_" + str(title), BlackboardAttribute.
TSK_BLACKBOARD_ATTRIBUTE_VALUE_TYPE.STRING, unicode(title))
artID_art = skCase.addBlackboardArtifactType(
"TSK_" + filetype + "_DATA", filetype)
except:
pass
getArtId = skCase.getArtifactTypeID("TSK_" + filetype + "_DATA")
for i in result:
art = i["handle"].newArtifact(getArtId)
for title in titles:
try:
art.addAttribute(
BlackboardAttribute(
skCase.getAttributeType("TSK_" + filetype + "_" +
str(title)),
DocumentMetadataIngestModuleFactory.moduleName,
unicode(i[title])))
except:
art.addAttribute(
BlackboardAttribute(
skCase.getAttributeType("TSK_" + filetype + "_" +
str(title)),
DocumentMetadataIngestModuleFactory.moduleName,
""))
def startModule(self, extension, skCase, fileManager, dataSource,
progressBar):
files = fileManager.findFiles(dataSource, "%." + extension)
numFiles = len(files)
progressBar.switchToDeterminate(numFiles)
fileCount = 0
Directory = os.path.join(Case.getCurrentCase().getTempDirectory(),
extension + " files")
try:
os.mkdir(Directory)
except:
pass
for file in files:
self.log(Level.INFO, "Processing file: " + file.getName())
fileCount += 1
self.totalCount += 1
Path = os.path.join(Directory, unicode(file.getName()))
ContentUtils.writeToFile(file, File(Path))
if extension.lower() == "pdf":
try:
resultPDF, resultNoModule = self.pdf.run(Path)
resultPDF["handle"] = file
resultNoModule["handle"] = file
self.PyPDF_result.append(resultPDF)
self.PDFNoModule_result.append(resultNoModule)
except:
pass
elif extension.lower() == "xlsx":
try:
OOXML = self.ooxml.run(Path)
OOXML["handle"] = file
self.xlsx_result.append(OOXML)
except:
pass
elif extension.lower() == "pptx":
try:
OOXML = self.ooxml.run(Path)
OOXML["handle"] = file
self.pptx_result.append(OOXML)
except:
pass
elif extension.lower() == "docx":
try:
OOXML = self.ooxml.run(Path)
OOXML["handle"] = file
self.docx_result.append(OOXML)
except:
pass
elif extension.lower() == "xls":
try:
resultCFBF = self.cfbf.run(Path)
resultCFBF["handle"] = file
self.xls_result.append(resultCFBF)
except:
pass
elif extension.lower() == "ppt":
try:
resultCFBF = self.cfbf.run(Path)
resultCFBF["handle"] = file
self.ppt_result.append(resultCFBF)
except:
pass
elif extension.lower() == "doc":
try:
resultCFBF = self.cfbf.run(Path)
resultCFBF["handle"] = file
self.doc_result.append(resultCFBF)
except:
pass
progressBar.progress(fileCount)
if extension.lower() == "pdf":
titles = self.getTitles(self.PyPDF_result)
self.addData(titles, self.PyPDF_result, "PyPDF", skCase)
titles = self.getTitles(self.PDFNoModule_result)
self.addData(titles, self.PDFNoModule_result, "PDFNoModule",
skCase)
elif extension.lower() == "xlsx":
titles = self.getTitles(self.xlsx_result)
self.addData(titles, self.xlsx_result, "XLSX", skCase)
elif extension.lower() == "pptx":
titles = self.getTitles(self.pptx_result)
self.addData(titles, self.pptx_result, "PPTX", skCase)
elif extension.lower() == "docx":
titles = self.getTitles(self.docx_result)
self.addData(titles, self.docx_result, "DOCX", skCase)
elif extension.lower() == "xls":
titles = self.getTitles(self.xls_result)
self.addData(titles, self.xls_result, "XLS", skCase)
elif extension.lower() == "ppt":
titles = self.getTitles(self.ppt_result)
self.addData(titles, self.ppt_result, "PPT", skCase)
elif extension.lower() == "doc":
titles = self.getTitles(self.doc_result)
self.addData(titles, self.doc_result, "DOC", skCase)
def process(self, dataSource, progressBar):
progressBar.switchToIndeterminate()
skCase = Case.getCurrentCase().getSleuthkitCase()
fileManager = Case.getCurrentCase().getServices().getFileManager()
self.startModule("pdf", skCase, fileManager, dataSource, progressBar)
self.startModule("docx", skCase, fileManager, dataSource, progressBar)
self.startModule("pptx", skCase, fileManager, dataSource, progressBar)
self.startModule("xlsx", skCase, fileManager, dataSource, progressBar)
self.startModule("doc", skCase, fileManager, dataSource, progressBar)
self.startModule("ppt", skCase, fileManager, dataSource, progressBar)
self.startModule("xls", skCase, fileManager, dataSource, progressBar)
message = IngestMessage.createMessage(
IngestMessage.MessageType.DATA, "DocumentMetadataParser",
"Found %d files" % self.totalCount)
IngestServices.getInstance().postMessage(message)
return IngestModule.ProcessResult.OK
outlines, next_outlines = itertools.tee(outlines, 2)
next_outlines = itertools.chain(itertools.islice(next_outlines, 1, None), [None])
return outlines, next_outlines
if __name__ == "__main__":
import get_pdf
from test_cases import test_cases
from get_data import HKEX_API
from helper import write_to_csv, n_yearsago, today
# logging.basicConfig(level=logging.INFO)
# query = HKEX_API(from_date=n_yearsago(n=1), to_date=today())
# for data in query.data:
# result = {}
# url = data.file_link
# pdf = PDF(url)
# print(url)
# f = TableOfContent(pdf.pdf_obj)
# print()
# result['result'] = f.search_outline_page_range(TableOfContent.auditor_remunration_regex)
# result['url'] = url
# write_to_csv(result, 'result_2.csv')
url = 'https://www1.hkexnews.hk/listedco/listconews/sehk/2020/0813/2020081300777.pdf'
url = 'https://www1.hkexnews.hk/listedco/listconews/sehk/2020/0813/2020081300670.pdf'
pdf = PDF(url)
print(url)
f = TableOfContent(pdf.pdf_obj)
print(f.search_outline_page_range(TableOfContent.audit_fee_regex))
if "--tex-all" in sys.argv:
conf["TeXing"]["force TeXing of all files"] = "yes"
revue = cr.Revue.fromfile("aktoversigt.plan")
path = revue.conf["Paths"]
conv = cv.Converter()
if len(conf.cmd_parts) == 0:
arglist = ("aktoversigt", "roles", "frontpage", "props", "contacts",
"material", "individual", "songmanus")
elif "manus" in sys.argv:
arglist = ("aktoversigt", "roles", "frontpage", "props", "contacts",
"material")
else:
arglist = sys.argv[1:]
create_parts(revue, arglist)
if len(conf.cmd_parts) == 0 or "manus" in sys.argv:
pdf = PDF()
pdf.pdfmerge(
((os.path.join(path["pdf"], "forside.pdf"), "Forside"),
(os.path.join(path["pdf"], "aktoversigt.pdf"), "Aktoversigt"),
(os.path.join(path["pdf"],
"rolleliste.pdf"), "Rolleliste"), revue,
(os.path.join(path["pdf"], "rekvisitliste.pdf"), "Rekvisitliste"),
(os.path.join(path["pdf"], "kontaktliste.pdf"), "Kontaktliste")),
os.path.join(path["pdf"], "manuskript.pdf"))
print("Manuscript successfully created!")
def doExport( self, event=None ):
race = Model.race
if not race:
return
fileName = Utils.getMainWin().fileName if Utils.getMainWin() else 'Test.cmn'
#---------------------------------------------------------------------------------
# Create an Excel file.
#
xlFileName = os.path.splitext(fileName)[0] + '-TeamResults.xlsx'
try:
wb = xlsxwriter.Workbook( xlFileName )
formats = ExportGrid.ExportGrid.getExcelFormatsXLSX( wb )
ues = Utils.UniqueExcelSheetName()
for category in race.getCategories( publishOnly=True ):
eg = self.toExportGrid( category )
if eg:
ws = wb.add_worksheet( ues.getSheetName(category.fullname) )
eg.toExcelSheetXLSX( formats, ws )
wb.close()
except Exception as e:
logException( e, sys.exc_info() )
del wb
#---------------------------------------------------------------------------------
# Create a PDF file.
#
pdfFileName = os.path.splitext(fileName)[0] + '-TeamResults.pdf'
try:
pdf = PDF( orientation = 'P' )
pdf.set_font( 'Arial', '', 12 )
pdf.set_author( getpass.getuser() )
pdf.set_keywords( 'CrossMgr Team Results' )
pdf.set_creator( Version.AppVerName )
pdf.set_title( os.path.splitext(pdfFileName)[0].replace('-', ' ') )
for category in race.getCategories( publishOnly=True ):
eg = self.toExportGrid( category )
if eg:
eg.drawToFitPDF( pdf, orientation=wx.PORTRAIT )
pdf.output( pdfFileName, 'F' )
except Exception as e:
logException( e, sys.exc_info() )
del pdf
def pdf(request):
pdf = PDF(request.display_user)
return pdf.as_response()
def vectorize(self,
path,
ignore_if_html_file_exists=True,
ignore_errors=False,
num_threads=1):
"""
:type path: str or Path
:type ignore_if_html_file_exists: bool
:type ignore_errors: bool
:rtype: DataFrame
"""
path = Path(path)
pdf_paths = [
PDF(file_path) for file_path in path.list(show_size=False)
if file_path.extension.lower() == 'pdf'
]
exceptions = []
# create htmls
for pdf_path in iterate(iterable=pdf_paths,
text='converting pdfs to html'):
try:
pdf_path.convert_to_html(
ignore_if_exists=ignore_if_html_file_exists)
except Exception as e:
if ignore_errors:
exceptions.append(e)
else:
raise e
# get paragraphs
def extract_paragraphs(pdf_path):
try:
pdf_paragraphs = pdf_path.paragraphs
num_paragraphs = len(pdf_paragraphs)
return [{
'pdf': pdf_path,
'paragraph_num': i + 1,
'paragraph': paragraph,
'num_paragraphs': num_paragraphs
} for i, paragraph in enumerate(pdf_paragraphs)]
except Exception as e:
if ignore_errors:
return [{'error': e}]
else:
raise e
if num_threads == 1:
paragraph_dict_lists = [
extract_paragraphs(x) for x in iterate(
pdf_paths, text='extracting paragraphs (single-threaded)')
]
else:
processor = Parallel(n_jobs=num_threads,
backend='threading',
require='sharedmem')
paragraph_dict_lists = processor(
delayed(extract_paragraphs)(pdf_path=x) for x in iterate(
pdf_paths, text='extracting paragraphs (multi-threaded)'))
paragraph_dicts = [
x for paragraph_dict_list in paragraph_dict_lists
for x in paragraph_dict_list
]
# create vectors
def get_vector_and_num_tokens(paragraph_dict):
try:
pdf_path = paragraph_dict['pdf']
paragraph_num = paragraph_dict['paragraph_num']
paragraph = paragraph_dict['paragraph']
num_paragraphs = paragraph_dict['num_paragraphs']
vector, num_tokens = self._bert_vectorizer.vectorize(
text=paragraph, get_num_tokens=True)
vector_df = DataFrame(
vector,
columns=[f'bert_{i + 1}' for i in range(vector.shape[1])])
vector_df['pdf'] = pdf_path.name_and_extension
vector_df['num_paragraphs'] = num_paragraphs
vector_df['paragraph_num'] = paragraph_num
vector_df['num_tokens'] = num_tokens
return vector_df
except Exception as e:
if ignore_errors:
return e
else:
raise e
if num_threads == 1:
vectors = [
get_vector_and_num_tokens(paragraph_dict=x) for x in iterate(
paragraph_dicts,
text='converting paragraphs to vectors (single-threaded)')
]
else:
processor = Parallel(n_jobs=num_threads,
backend='threading',
require='sharedmem')
vectors = processor(
delayed(get_vector_and_num_tokens)(paragraph_dict=x)
for x in iterate(
paragraph_dicts,
text='converting paragraphs to vectors (multi-threaded)'))
return bring_to_front(
data=concat(vectors),
columns=['pdf', 'paragraph_num', 'num_paragraphs',
'num_tokens']).reset_index(drop=True)
class CrossMgrPrintoutPDF( CrossMgrPrintout ):
def __init__( self, dir, fileBase, orientation, categories = None, allInOne = False ):
CrossMgrPrintout.__init__(self, categories)
self.dir = dir
self.fileBase = fileBase
self.orientation = orientation
self.allInOne = allInOne
self.pdf = None
self.lastFName = None
def OnEndPrinting(self):
if self.pdf and self.allInOne:
if self.dir and not os.path.isdir( self.dir ):
os.mkdir( self.dir )
fname = u'{fileBase}.pdf'.format( fileBase=self.fileBase )
self.pdf.set_title( unicode(os.path.splitext(fname)[0].replace('-', ' ')).encode('iso-8859-1','ignore') )
fname = os.path.join( self.dir, fname )
self.pdf.output( fname, 'F' )
self.lastFName = fname
self.pdf = None
return super(CrossMgrPrintoutPDF, self).OnEndPrinting()
def OnPrintPage( self, page ):
exportGrid = self.prepareGrid( page )
try:
category = self.pageInfo[page][0]
except Exception as e:
# Handle case of no data.
return True
pageNumber = self.pageInfo[page][3]
pageTotal = self.pageInfo[page][4]
fname = u'{fileBase}-{categoryName}.pdf'.format(
fileBase = self.fileBase,
categoryName = category.fullname if category != 'Primes' else 'Primes'
)
fname = Utils.RemoveDisallowedFilenameChars( fname ).replace( ' ', '-' )
if not self.pdf:
self.pdf = PDF( orientation = 'L' if self.orientation == wx.LANDSCAPE else 'P' )
self.pdf.set_font( 'Arial', '', 12 )
self.pdf.set_author( unicode(getpass.getuser()).encode('iso-8859-1','ignore') )
self.pdf.set_keywords( unicode('CrossMgr Results').encode('iso-8859-1','ignore') )
self.pdf.set_creator( unicode(Version.AppVerName).encode('iso-8859-1','ignore') )
self.pdf.set_title( unicode(os.path.splitext(fname)[0].replace('-', ' ')).encode('iso-8859-1','ignore') )
exportGrid.drawToFitPDF( *([self.pdf, self.orientation] + self.pageInfo[page][1:-1]) )
if not self.allInOne and pageNumber == pageTotal:
if self.dir and not os.path.isdir( self.dir ):
os.mkdir( self.dir )
fname = os.path.join( self.dir, fname )
self.pdf.output( fname, 'F' )
self.lastFName = fname
self.pdf = None
return True
return f'{self.__class__.__name__} - {self.section}'
if __name__ == '__main__':
from hkex_api import HKEX_API
# https://www1.hkexnews.hk/listedco/listconews/gem/2020/0929/2020092901098.pdf #concat number
# https://www1.hkexnews.hk/listedco/listconews/sehk/2020/0929/2020092900604.pdf #concat number
query = HKEX_API()
urls = [data.file_link for data in query.get_data()]
# urls = ['https://www1.hkexnews.hk/listedco/listconews/sehk/2020/0923/2020092300374.pdf']
for url in urls:
# url = data.file_link
# url, p = 'https://www1.hkexnews.hk/listedco/listconews/sehk/2020/0721/2020072100713.pdf', 61
# url, p = 'https://www1.hkexnews.hk/listedco/listconews/sehk/2020/0721/2020072100653.pdf', 94
print(url)
pdf = PDF.create(url)
corp_gov_report = pdf.get_outline(CorporateGovReport.title_regex)
if not corp_gov_report:
continue
corp_gov_report = CorporateGovReport.create(corp_gov_report[0])
if not corp_gov_report:
continue
if not corp_gov_report.audit_fee:
continue
try:
page = corp_gov_report.audit_fee.pages[0]
sec = corp_gov_report.audit_fee.sections[0]
table = corp_gov_report.audit_fee.tables[0]
except Exception as e:
print(e)
continue
text = ''.join(i for i in temp if isinstance(i,basestring))
return text
password = ''
print sys.argv
fp = open(sys.argv[1], 'rb')
parser = PDFParser(fp)
document = PDFDocument(parser)
document.initialize(password)
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
pdf = PDF(sys.argv[1],verbose=True)
page_no = 1
for page in PDFPage.create_pages(document):
interpreter.process_page(page)
# receive the LTPage object for the page.
layout = device.get_result()
for group in layout.groups:
rect = [group.x0,group.y0,group.x1,group.y1]
quad = [
group.x0,group.y0,
group.x1,group.y0,
group.x1,group.y1,
group.x0,group.y1
]
pdf.add_annot_to_page(page_no,quad,rect)
