feat/pypdf: bump pypdf. (#16)

* dep: upgrade PyPDF2 to pypdf==3.7.1

* refactor: update pypdf api usage.

* doc: update.

* chore: update sample output with pypdf.

README.md

@@ -96,7 +96,8 @@ Known limitation:
 
 ## Dependency
 
-- PyPDF2: edit the pdf box
+- pypdf: a pure python module for pdf (upgrade of PyPDF2)
+- ~~PyPDF2: edit the pdf box~~
 - ~~pdfminer & pdfminer3: scan elements~~
 - pdfminer.six: scan pdf elements
 - ~~PySide2: optional for GUI only~~

pdf_page_split/Readme.md

@@ -13,7 +13,7 @@
   - 输出所有的对应latex语句（template.tex）中可以修改
 
 # 使用
-- python3 -m pip install PyPDF2
+- python3 -m pip install -r requirements.txt
 - python3 splitor.py -t figure.tex -c figure.csv -o split/figure testcase.pdf
   - `-t`选择模板，只有figure和table两类（也可以执行修改）
   - `-c`选择数据文件

pdf_page_split/splitor.py

@@ -1,15 +1,12 @@
 # coding=utf-8
 import argparse
-import PyPDF2 as pdflib
-from PyPDF2 import PdfFileWriter, PdfFileReader
-
+import configparser
+import csv
+import logging
 import os
 import sys
-import logging
-
 
-import configparser
-import csv
+from pypdf import PdfReader, PdfWriter
 
 # from config import config
 
@@ -113,7 +110,7 @@ def split(path, template, config, output="split", no_pdf=False):
     with open(path, "rb") as pdf, open(
         "log.txt".format(output), "w", encoding="utf-8"
     ) as log:
-        reader = PdfFileReader(pdf)
+        reader = PdfReader(pdf)
 
         for i, item in zip(range(reader.getNumPages()), config):
             if item is None:
@@ -130,7 +127,7 @@ def split(path, template, config, output="split", no_pdf=False):
             page = reader.getPage(i)
 
             if not no_pdf:
-                writer = PdfFileWriter()
+                writer = PdfWriter()
                 writer.add_page(page)
                 with open("{}".format(path), "wb") as figure:
                     writer.write(figure)

pdf_white_cut/cutter.py

@@ -1,7 +1,7 @@
 import os
 
-from PyPDF2 import PdfWriter, PdfReader
 from path import Path
+from pypdf import PdfReader, PdfWriter
 
 from pdf_white_cut import analyzer
 from pdf_white_cut.logger import logger
@@ -55,7 +55,7 @@ def edit_pdf(source: Path, target: Path, ignore=0):
     try:
         # MENTION: never move and change the sequence, since file IO.
         # analyses the visible box of each page, aka the box scale. res=[(x1,y1,x2,y2)]
-        # analyses whole pdf at one time since it use `pdfminer` (not `PyPDF2`)
+        # analyses whole pdf at one time since it use `pdfminer` (not `pypdf`)
         page_box_list = analyzer.extract_pdf_boxs(source, ignore=ignore)
 
         # edit pdf by visible box and output it

requirements.txt

@@ -1,5 +1,5 @@
 # required
-PyPDF2==2.11.1
+pypdf==3.7.1
 pdfminer.six
 loguru==0.6.0
 path

tests/test_PyPDF2.py → tests/test_pypdf.py

@@ -1,7 +1,7 @@
-from PyPDF2 import PdfFileWriter, PdfFileReader
+from pypdf import PdfReader, PdfWriter
 
-output = PdfFileWriter()
-input1 = PdfFileReader(open("cases/input/input.pdf", "rb"))
+output = PdfWriter()
+input1 = PdfReader(open("cases/input/input.pdf", "rb"))
 
 # print how many pages input1 has:
 print("document1.pdf has %d pages." % input1.getNumPages())
@@ -18,15 +18,15 @@
 
 # add page 4 from input1, but first add a watermark from another PDF:
 page4 = input1.getPage(3)
-watermark = PdfFileReader(open("input.pdf", "rb"))
+watermark = PdfReader(open("input.pdf", "rb"))
 page4.mergePage(watermark.getPage(0))
 output.add_page(page4)
 
 # add page 5 from input1, but crop it to half size:
 page5 = input1.getPage(4)
-page5.mediaBox.upperRight = (
-    page5.mediaBox.getUpperRight_x() / 2,
-    page5.mediaBox.getUpperRight_y() / 2,
+page5.mediabox.upperRight = (
+    page5.mediabox.getUpperRight_x() / 2,
+    page5.mediabox.getUpperRight_y() / 2,
 )
 output.add_page(page5)
 

tests/test_white_cut.py

@@ -1,7 +1,7 @@
 import sys
 
 import loguru
-from PyPDF2 import PdfFileReader, PdfFileWriter
+from pypdf import PdfReader, PdfWriter
 
 sys.path.append(".")
 
@@ -28,13 +28,12 @@ def test_analyzer():
 
 
 def test_rw_pdf():
-
-    pdf = PdfFileReader(open("cases/input/input.pdf", "rb"))
-    out = PdfFileWriter()
+    pdf = PdfReader(open("cases/input/input.pdf", "rb"))
+    out = PdfWriter()
 
     for page in pdf.pages:
-        page.mediaBox.upper_right = (580, 800)
-        page.mediaBox.lower_left = (128, 232)
+        page.mediabox.upper_right = (580, 800)
+        page.mediabox.lower_left = (128, 232)
         out.add_page(page)
 
     ous = open("cases/output/output.pdf", "wb")