def get_paper_content(fname, pages=2, outdir="data"):
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
basename = os.path.basename(fname)
basename = basename.replace(".pdf", "")
outfile = os.path.join(outdir, basename + ".html")
outtype = None
imagewriter = None
rotation = 0
stripcontrol = False
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFPageInterpreter.debug = debug
#
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr,
outfp,
codec=codec,
scale=scale,
layoutmode=layoutmode,
laparams=laparams,
imagewriter=imagewriter,
debug=debug)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
else:
return
fp = file(fname, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
interpreter.debug = True
try:
for index, page in enumerate(
PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True)):
if index > pages:
break
page.rotate = (page.rotate + rotation) % 360
interpreter.process_page(page)
except:
print(fname)
return
fp.close()
device.close()
outfp.close()
return
from pdfminer.layout import LAParams
from pdfminer.converter import XMLConverter
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
laparams = LAParams()
imagewriter = None
codec = 'utf-8'
outfp = sys.stdout
stripcontrol = True
pagenos = set()
fname = sys.argv[1]
rsrcmgr = PDFResourceManager(caching=True)
device = XMLConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
fp = file(fname, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
interpreter.debug = 1
for page in PDFPage.get_pages(fp, pagenos,
maxpages=0, password='',
caching=True, check_extractable=True):
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
laparams = LAParams()
imagewriter = None
codec = 'utf-8'
outfp = sys.stdout
stripcontrol = True
pagenos = set()
fname = sys.argv[1]
rsrcmgr = PDFResourceManager(caching=True)
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter,
stripcontrol=stripcontrol)
fp = file(fname, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
interpreter.debug = 1
for page in PDFPage.get_pages(fp,
pagenos,
maxpages=0,
password='',
caching=True,
check_extractable=True):
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
