spider/js_reverse
1
0
Fork 0
mirror of https://github.com/luzhisheng/js_reverse.git synced 2025-04-21 00:25:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

pdf 处理

Browse Source
This commit is contained in:
aiyingfeng 2023-07-24 18:43:27 +08:00
parent b8f68e3a45
commit c0cdf2f8b5
1 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
pdf处理/program/discern.py
View File

@ -1,6 +1,7 @@
import image_compare import image_compare
import pandas as pd import pandas as pd
import pdfplumber import pdfplumber
import PyPDF2
from image_text_ocr import ImageTextOcr from image_text_ocr import ImageTextOcr
import os import os
import cv2 import cv2
@ -51,15 +52,18 @@ class Discern(object):
def pdf_images(self, pdf_path): def pdf_images(self, pdf_path):
self.num = 0 self.num = 0
with pdfplumber.open(pdf_path) as pdf: pdf_reader = PyPDF2.PdfReader(pdf_path)
for page in pdf.pages: for page_num in range(len(pdf_reader.pages)):
images = page.images page = pdf_reader.pages[page_num]
for img in images: xObject = page['/Resources']['/XObject'].get_object()
# 获取图片的二进制流
for obj in xObject:
if xObject[obj]['/Subtype'] == '/Image':
size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
self.num += 1 self.num += 1
image_file = f"../target_img/image_{self.num}.png" image_file = f"../target_img/image_{self.num}.png"
with open(image_file, "wb") as f: with open(image_file, "wb") as f:
f.write(img['stream'].get_data()) f.write(xObject[obj].get_data())
def get_images_text(self): def get_images_text(self):
for i in range(1, self.num + 1): for i in range(1, self.num + 1):