def get_page_heirarchy(filename):
pdf_data = sh.pdftk(filename, "dump_data")
rows = []
record = {}
for row in pdf_data.split('\n'):
if row.startswith('BookmarkTitle'):
title = row.split(": ")[1]
record['title'] = title.strip()
if row.startswith('BookmarkLevel'):
level = int(row.split(": ")[1])
record['level'] = level
if row.startswith('BookmarkPageNumber'):
pn = int(row.split(": ")[1])
record['page'] = pn
record['children'] = []
rows.append(record)
record = {}
heir = {'title': "Root", "level": 0, 'pn': 0, "children": []}
build_heirarchy(heir, rows)
monsters = None
after = None
for rec in heir['children']:
if monsters != None:
after = rec
break
if rec['title'].startswith('Monsters'):
monsters = rec
fix_letters(monsters)
fix_introduction(monsters)
fix_duplicate_names(monsters)
fix_apostrophe(monsters)
fix_leaf_ray(monsters)
fix_submonsters(monsters)
fix_dragons(monsters)
fix_assassin_vine(monsters)
return monsters, after['page']
def generate_pdfs(persons, maßnahmenzeitraum, datum, kif_ev, maßname,
leer_blaetter):
seite = 1
data_file = "data_fdf.bin"
output_file_name = "output"
personen_pro_seite = 14
#check if vorlage exits
test_file = Path(vorlage)
if not test_file.is_file():
print("[X] File {} not found!".format(vorlage))
exit(-1)
anzahl_seiten = ceil(len(persons) / personen_pro_seite)
pdfs = []
for j in range(anzahl_seiten + leer_blaetter):
felder = []
i = 0
for item in form_mapping:
if personen_pro_seite * j + i < len(persons):
felder.append((item[0], str(j * personen_pro_seite + i + 1)))
felder.append(
(item[1], persons[j * personen_pro_seite + i]["Name"]))
felder.append(
(item[2],
persons[j * personen_pro_seite + i]["Hochschule"]))
i += 1
if i == personen_pro_seite:
output_file = output_file_name + str(seite) + ".pdf"
headers = [("1", seite), ("2", maßnahmenzeitraum),
("3", datum), ("4", kif_ev), ("5", maßname)]
fields = felder + headers
fdf = forge_fdf("", fields, [], [], [])
fdf_file = open(data_file, "wb")
fdf_file.write(fdf)
fdf_file.close()
sh.pdftk(vorlage, "fill_form", data_file, "output",
output_file, "flatten")
pdfs.append(output_file)
seite += 1
return pdfs
def exec_pdftk(filename):
stdout = BytesIO()
stderr = StringIO()
sh.pdftk(
filename,
'output', '-',
'dont_ask',
'flatten',
_out=stdout,
_err=stderr
)
stderr = stderr.getvalue()
if stderr.strip():
raise IOError(stderr)
return stdout
def _exec_pdftk(pdf, items, outfile):
stderr = StringIO()
fdf = forge_fdf("", items, [], [], [])
# pylint: disable=E1101
sh.pdftk(pdf,
"fill_form",
"-",
"output",
outfile,
"dont_ask",
"flatten",
_in=fdf,
_err=stderr)
stderr = stderr.getvalue()
if stderr.strip():
raise IOError(stderr)
def save_the_beasts(filename, directory, heir, last_page):
if not os.path.exists(directory):
os.mkdir(directory)
for i in range(0, len(heir['children'])):
row = heir['children'][i]
next_page = last_page
if len(heir['children']) > i+1:
next_page = heir['children'][i+1]['page']
last_page = next_page - 1
if last_page < row['page']:
last_page = row['page']
title = row['title']
pagedir = directory
subdir = title[0]
pagedir = "%s/%s" % (directory, subdir)
if not os.path.exists(pagedir):
os.mkdir(pagedir)
newfile = "%s/%s.pdf" %(pagedir, row['title'])
print "%s: %s-%s" %(newfile, row['page'], last_page)
if os.path.exists(newfile):
sys.stderr.write("!!!!%s Already Exists\n" % newfile)
else:
sh.pdftk(filename, "cat", "%s-%s" %(
row['page'], last_page), "output", newfile)
latex_footer = """
\end{document}
"""
if len(sys.argv) < 3:
print(usage)
sys.exit(1)
input_file = sys.argv[1]
output_file = input_file[:-4] + '_titles' + '.pdf'
# Get a list of all the titles
# Make sure that there are at least as many titles as input pages
titles = sys.argv[2:]
pdfinfo = pdftk(input_file, 'dump_data')
pdfinfol = pdfinfo.strip().split('\n')
pdfpages = pdfinfol[-1].split(':')
numpages = int(pdfpages[1].strip())
while numpages > len(titles):
titles.append('~')
# Combine the headers and create a .tex file with the headers
latex_titles = ' \\newpage\n'.join(titles)
latex_out = latex_header + latex_titles + latex_footer
with open(TITLES_TEX, 'w') as f:
f.write(latex_out)
latex_footer = """
\\end{document}
"""
if len(sys.argv) < 3:
print(usage)
sys.exit(1)
input_file = sys.argv[1]
output_file = input_file[:-4] + '_titles' + '.pdf'
# Get a list of all the titles
# Make sure that there are at least as many titles as input pages
titles = sys.argv[2:]
pdfinfo = pdftk(input_file, 'dump_data')
pdfinfol = pdfinfo.strip().split('\n')
for line in pdfinfol:
items = line.split(':')
if len(items) == 2 and items[0] == 'NumberOfPages':
numpages = int(items[1].strip())
break
while numpages > len(titles):
titles.append('~')
# Combine the headers and create a .tex file with the headers
latex_titles = ' \\newpage\n'.join(titles)
latex_out = latex_header + latex_titles + latex_footer
color: black;
font-size: 16px;
display: block;
text-align: center;
}
em {
color: black;
font-size: 0.9em;
}
"""
prog = u"""
<html>
<head>
<meta http-equiv="content-type" content="text/html;charset=utf-8" />
</head>
<body>
<h1 id="maintitle">SciPy Latin America 2015<br>Schedule</h1>
{prog}
<style>{style}</style>
</body>
</html>""".format(style=style, prog=prog)
with codecs.open(HTML_PATH, "w", encoding="utf8") as fp:
fp.write(prog)
sh.wkhtmltopdf(HTML_PATH, PDF_PATH)
sh.pdftk(PDF_PATH, PUBS_PATH, "cat", "output", PROG_PATH)
# pdf is bigger than the test pdf
test_size = os.stat('{}_layer_test.pdf'.format(sch_name)).st_size
layer2_size = os.stat('{}_layer2_copper.pdf'.format(sch_name)).st_size
layer3_size = os.stat('{}_layer3_copper.pdf'.format(sch_name)).st_size
if layer2_size > test_size or layer3_size > test_size:
layer_count = 4
# Combine them
pdfs = []
titles = []
for pdf, title in pdf_files:
if ('layer2' in pdf or 'layer3' in pdf) and layer_count == 2:
continue
pdfname = '{}_{}.pdf'.format(sch_name, pdf)
if os.path.exists(pdfname):
pdfinfo = pdftk(pdfname, 'dump_data')
pdfinfol = pdfinfo.strip().split('\n')
pdfpages = pdfinfol[-1].split(':')
numpages = int(pdfpages[1].strip())
titles += [title]*numpages
pdfs.append(pdfname)
if include_bom:
pdfs.append('{}_bom.pdf'.format(sch_name))
args = pdfs + ['cat', 'output', '{}.pdf'.format(sch_name)]
pdftk(*args)
# Delete the generated pdfs if they exist
for pdf, title in pdf_files + [('layer_test', '~')]:
try:
def _invoke_pdftk(*args, outname):
assert outname
sh.pdftk(*args, "cat", "output", outname)
output_file = output_file_name + str(seite) + ".pdf"
headers = [("1", seite), ("2", maßnahmenzeitraum),
("3", datum), ("4", kif_ev), ("5", maßname)]
fields = felder + headers
fdf = forge_fdf("", fields, [], [], [])
fdf_file = open(data_file, "wb")
fdf_file.write(fdf)
fdf_file.close()
sh.pdftk(vorlage, "fill_form", data_file, "output",
output_file, "flatten")
pdfs.append(output_file)
seite += 1
return pdfs
if __name__ == "__main__":
person_list = readcsv(csv_file_name)
for datum in datum_list:
final_pdf_name = "teilnehmendenliste_{}.pdf".format(
datum.replace(". ", "_"))
output_files = generate_pdfs(person_list, maßnahmenzeitraum, datum,
kif_ev, maßname, leer_blaetter)
sh.pdftk(output_files, "cat", "output", final_pdf_name)
def run_pdftk(file):
buf = StringIO()
sh.pdftk(file, 'dump_data_fields_utf8', _out=buf)
return buf.getvalue()
# pdf is bigger than the test pdf
test_size = os.stat('{}_layer_test.pdf'.format(sch_name)).st_size
layer2_size = os.stat('{}_layer2_copper.pdf'.format(sch_name)).st_size
layer3_size = os.stat('{}_layer3_copper.pdf'.format(sch_name)).st_size
if layer2_size > test_size or layer3_size > test_size:
layer_count = 4
# Combine them
pdfs = []
titles = []
for pdf, title in pdf_files:
if ('layer2' in pdf or 'layer3' in pdf) and layer_count == 2:
continue
pdfname = '{}_{}.pdf'.format(sch_name, pdf)
if os.path.exists(pdfname):
pdfinfo = pdftk(pdfname, 'dump_data')
pdfinfol = pdfinfo.strip().split('\n')
for line in pdfinfol:
items = line.split(':')
if len(items) == 2 and items[0] == 'NumberOfPages':
numpages = int(items[1].strip())
break
titles += [title]*numpages
pdfs.append(pdfname)
if include_bom:
pdfs.append('{}_bom.pdf'.format(sch_name))
args = pdfs + ['cat', 'output', '{}.pdf'.format(sch_name)]
pdftk(*args)
# Delete the generated pdfs if they exist
text-align: center;
}
em {
color: black;
font-size: 0.9em;
}
"""
prog = u"""
<html>
<head>
<meta http-equiv="content-type" content="text/html;charset=utf-8" />
</head>
<body>
<h1 id="maintitle">SciPy Latin America 2015<br>Schedule</h1>
{prog}
<style>{style}</style>
</body>
</html>""".format(style=style, prog=prog)
with codecs.open(HTML_PATH, "w", encoding="utf8") as fp:
fp.write(prog)
sh.wkhtmltopdf(HTML_PATH, PDF_PATH)
sh.pdftk(PDF_PATH, PUBS_PATH, "cat", "output", PROG_PATH)