saberbud/pdfplumber
1
0
Fork 0
mirror of https://github.com/jsvine/pdfplumber.git synced 2026-08-29 08:34:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add pages option for processing only some pages

Browse Source
This commit is contained in:
Jeremy Singer-Vine
2015-08-27 14:43:02 -04:00
parent b3a7cb8359
commit 7ccfb57d52
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pdfplumber/pdf.py
+4 -2
View File
@@ -13,7 +13,7 @@ from pdfminer.layout import LAParams, LTChar, LTImage, LTPage
from pdfminer.converter import PDFPageAggregator
class PDF(object):
def __init__(self, file_or_buffer, pandas=False, laparams={}):
def __init__(self, file_or_buffer, pages=None, pandas=False, laparams={}):
self.pandas = pandas
self.laparams = LAParams(**laparams)
@@ -23,7 +23,9 @@ class PDF(object):
self.interpreter = PDFPageInterpreter(rsrcmgr, self.device)
self.pages = []
for page in PDFPage.create_pages(self.doc):
page_iter = (p for i, p in enumerate(PDFPage.create_pages(self.doc))
if pages == None or i+1 in pages)
for page in page_iter:
self.interpreter.process_page(page)
layout = self.device.get_result()
self.pages.append(layout)