def process_pdf(self, pdffile, skippage):
basefile = fo.get_base_filename(pdffile)
outfile = "{}/{}.csv".format(self.outdir, basefile)
tempout = "{}/{}.csv".format(self.tempdir, basefile)
dqout = "{}/dq.xlsx".format(self.dqoutdir, )
filelist = self.preprocess_pdf(pdffile=pdffile, html_dir=self.htmldir)
filecounter = 1
tempfileno = open(tempout, 'wt', encoding='utf-8', newline="")
tempwriter = csv.writer(tempfileno, delimiter=",")
try:
for htmlfile in filelist:
if int(
str(fo.get_base_filename(htmlfile)).replace(
"page", "")) <= skippage:
continue
tempfile = "{0}/{1}_temp.csv".format(
self.tempdir, fo.get_base_filename(htmlfile))
self.process_pdf_tab(pdffile=pdffile,
htmlfile=htmlfile,
outfile=tempfile,
begin=self.begin,
end=self.end,
runtype=self.runtype)
cp.arrange_csv(
tempfile,
outfile=tempwriter,
pivotcol=self.pivotcolumn,
pivotregexp=self.regexppivot,
ignorecounter=0,
multipage=True,
fileno=filecounter,
headercol=2,
)
filecounter += 1
except Exception:
raise
finally:
tempfileno.close()
self._process_csv(tempout, outfile, self.addressindex)
self.dq_check(auditfile=self.auditfile,
pdffile=pdffile,
outfile=outfile,
auditout=dqout)
# - ビル名称
# - 竣工
# - 所在地
# - 最寄駅
# - フロア
# - 面積 (m2)
# - 面積 (坪)
# - 入居時期
# - 備考
# - 担当者
# - 連絡先TEL
def process_pdf(self, pdffile, skippage):
basefile = fo.get_base_filename(pdffile)
outfile = "{}/{}.csv".format(self.outdir, basefile)
tempout = "{}/{}.csv".format(self.tempdir, basefile)
filelist = self.preprocess_pdf(pdffile=pdffile, html_dir=self.htmldir)
print(filelist)
filecounter = 1
tempfileno = open(tempout, 'wt', encoding='utf-8', newline="")
tempwriter = csv.writer(tempfileno, delimiter=",")
try:
for htmlfile in filelist:
if fo.get_base_filename(htmlfile) == 'page' + str(skippage):
continue
tempfile = "{0}/{1}_temp.csv".format(
self.tempdir, fo.get_base_filename(htmlfile))
self.process_pdf_tab(pdffile=pdffile,
htmlfile=htmlfile,
outfile=tempfile,
begin=self.begin,
end=self.end,
runtype=self.runtype)
cp.arrange_csv(tempfile,
outfile=tempwriter,
pivotcol=self.pivotcolumn,
pivotregexp=self.regexppivot,
ignorecounter=0,
multipage=True,
fileno=filecounter,
headercol=4)
filecounter += 1
except Exception:
raise
finally:
tempfileno.close()
self._process_csv(tempout, outfile)
#self.refill_csv(infile=tempout, outfile=outfile, ignorefirst=False)
# - ビル名称
# - 竣工
# - 所在地
# - 最寄駅
# - フロア
# - 面積 (m2)
# - 面積 (坪)
# - 入居時期
# - 備考
# - 担当者
# - 連絡先TEL
def import_audit_sheet(auditfile, pdffile):
"""
:param auditfile: location of the audit file
:param pdffile: file name of the PDF file with Path
:return: dataframe of the auditfile for the pdffile
"""
basefile = fo.get_base_filename(pdffile)
audit = pd.read_excel(auditfile)
filename = basefile.split('_')[0]
audit = audit[audit["FileName"] == filename]
return audit, basefile
def process_pdf(self, pdffile):
basefile = fo.get_base_filename(pdffile)
outfile = "{}/{}.csv".format(
self.outdir,
basefile
)
tempout = "{}/{}.csv".format(
self.tempdir,
basefile
)
dqout = "{}/dq.xlsx".format(
self.dqoutdir,
)
filelist = self.preprocess_pdf(pdffile=pdffile, html_dir=self.htmldir)
tempfileno = open(tempout, 'wt', encoding='utf-8', newline="")
tempwriter = csv.writer(tempfileno, delimiter=",")
filecounter = 1
try:
for htmlfile in filelist:
tempfile = "{0}/{1}_temp.csv".format(
self.tempdir,
fo.get_base_filename(htmlfile)
)
self.process_pdf_tab(
pdffile=pdffile, htmlfile=htmlfile, outfile=tempfile,
begin=self.begin, end=self.end, runtype = self.runtype
)
cp.arrange_csv(
tempfile, outfile=tempwriter, pivotcol=self.pivotcolumn,
pivotregexp=self.regexppivot, ignorecounter=0,
multipage=True, fileno=filecounter, headercol = 0
)
filecounter += 1
except Exception:
raise
finally:
tempfileno.close()
self._process_csv(tempout, outfile)
self.dq_check(auditfile=self.auditfile, pdffile=pdffile.replace("Apple","AppleResi"), outfile=outfile.replace("Apple","AppleResi"), auditout=dqout)
self.dq_check(auditfile=self.auditfile, pdffile=pdffile.replace("Apple","AppleRetail"), outfile=outfile.replace("Apple","AppleRetail"), auditout=dqout)
