def convPdf(portfolios_dir, f, verbose=0):
pdf_filepath = os.path.join(portfolios_dir, f)
toc=layout_scanner.get_toc(pdf_filepath)
if verbose > 0: print "TOC -- not currently used for dict"
if verbose > 0:
for e in toc: print e
pages=layout_scanner.get_pages(pdf_filepath)
doc_dict = {'doctype': "report", 'origin': "shareworks"}
doc_dict['_id'] = f
doc_dict['student_email'] = email_from_fname(f)
doc_dict['content'] = []
for (count, p) in enumerate(pages):
if len(p) > 5: # when is a page non-empty?
doc_dict['content'].append({'header': "Page %s" % count, 'text': p.decode('utf-8')})
if len(doc_dict['content']) == 0:
doc_dict['content'] = [{'text': 'FrozenCutlery', 'txt_ann': None}]
return doc_dict
def convPdf(portfolios_dir, f, verbose=0):
pdf_filepath = os.path.join(portfolios_dir, f)
toc = layout_scanner.get_toc(pdf_filepath)
if verbose > 0: print "TOC -- not currently used for dict"
if verbose > 0:
for e in toc:
print e
pages = layout_scanner.get_pages(pdf_filepath)
doc_dict = {'doctype': "report", 'origin': "shareworks"}
doc_dict['_id'] = f
doc_dict['student_email'] = email_from_fname(f)
doc_dict['content'] = []
for (count, p) in enumerate(pages):
if len(p) > 5: # when is a page non-empty?
doc_dict['content'].append({
'header': "Page %s" % count,
'text': p.decode('utf-8')
})
if len(doc_dict['content']) == 0:
doc_dict['content'] = [{'text': 'FrozenCutlery', 'txt_ann': None}]
return doc_dict
#!/usr/bin/evn python
# -*- coding: utf-8 -*-
import layout_scanner as ls
name = "m2.pdf"
rsname = "m2rs.txt"
fd = open(rsname, "wb+")
toc = ls.get_toc(name)
for u in toc:
print "level", u[0]
print "title", u[1]
tc = ls.get_pages(name, images_folder='img')
for u in tc:
#fd.write(u.decode('utf-8'))
print "type:", type(u)
print "str:",u.decode('utf-8')
a = u.decode('utf-8')
print "len u:", len(u)
print "len a:", len(a)
#for c in u:
#print "type c:", type(c)
#print c.decode('utf-8')
fd.write(u.decode('utf-8'))
import layout_scanner
toc=layout_scanner.get_toc('/Users/mattstringer/Dropbox/ProyectoLaCumbre/DataClean/pdfs/example_finca.pdf')
def getTOCFromLayoutScanner(filePath):
toc = layout_scanner.get_toc(filePath)
return toc
import layout_scanner
toc = layout_scanner.get_toc(
'/home/dpkm95/pes/4sem/ada/mini-project/Algorithms.pdf')
print toc
import layout_scanner
toc = layout_scanner.get_toc(
'/Users/mattstringer/Dropbox/ProyectoLaCumbre/DataClean/pdfs/example_finca.pdf'
)
import layout_scanner from cStringIO import StringIO file_and_name = '/home/hjiang/pmscrapy/pdf_folder/00000001.PDF' folder = '/home/hjiang/scrapy/' images_folder = '/homne/hjiang/scrapy/tmp/' file_name = '00002207.PDF' output_name = 'test2.txt' pwd = '' toc=layout_scanner.get_toc(file_and_name, pwd) len(toc) pages=layout_scanner.get_pages(file_and_name) # len(pages) for page in pages: layout_scanner.write_file(folder,output_name,page)
