Python reads text, tables, and pictures in PDF files

Python reads text, tables, and pictures in PDF files

Tip: After the article is written, the table of contents can be automatically generated. For how to generate it, please refer to the help document on the right.

---

1. Text reading

based on fitz

import fitz
pdf_file = "example.pdf"
pdf_document = fitz.open(pdf_file)
text = ""
for page_number in range(len(pdf_document)):
    page = pdf_document.load_page(page_number)
    for block in page.get_text("blocks"):
        x0, y0, x1, y1 = block[0:4]
        text_block = block[4]
        # 根据文本块属性过滤表格中的文本
        # 这只是一个示例，你可以根据文本块的位置和其他属性来进一步过滤
        if y1 - y0 < 20:  # 通过高度过滤小文本块
            continue
        if "image" in text_block:
            continue
        text += text_block
pdf_document.close()
print(text)

2. Image reading

based on fitz

import fitz
doc = fitz.open("example.pdf") # open a document
for page_index in range(len(doc)): # iterate over pdf pages
    page = doc[page_index] # get the page
    image_list = page.get_images()
    # print the number of images found on the page
    if image_list:
        print(f"Found {
      
      len(image_list)} images on page {
      
      page_index}")
    else:
        print("No images found on page", page_index)
    for image_index, img in enumerate(image_list, start=1): # enumerate the image list
        xref = img[0] # get the XREF of the image
        pix = fitz.Pixmap(doc, xref) # create a Pixmap
        if pix.n - pix.alpha > 3: # CMYK: convert to RGB first
            pix = fitz.Pixmap(fitz.csRGB, pix)
        pix.save("page_%s-image_%s.png" % (page_index, image_index)) # save the image as png
        pix = None

3. Table reading

based on fitz

import fitz
doc = fitz.open("example.pdf") # open a document
for page_index in range(len(doc)): # iterate over pdf pages
    page = doc[page_index] # get the page
    image_list = page.get_images()
    # print the number of images found on the page
    if image_list:
        print(f"Found {
      
      len(image_list)} images on page {
      
      page_index}")
    else:
        print("No images found on page", page_index)
    for image_index, img in enumerate(image_list, start=1): # enumerate the image list
        xref = img[0] # get the XREF of the image
        pix = fitz.Pixmap(doc, xref) # create a Pixmap
        if pix.n - pix.alpha > 3: # CMYK: convert to RGB first
            pix = fitz.Pixmap(fitz.csRGB, pix)
        pix.save("page_%s-image_%s.png" % (page_index, image_index)) # save the image as png
        pix = None

Based on fitz, extract tabular data as text content

import fitz
doc = fitz.open("example.pdf") # open a document
out = open("output.txt", "wb") # create a text output
for page in doc: # iterate the document pages
    text = page.get_text().encode("utf8") # get plain text (is in UTF-8)
    out.write(text) # write text of page
    out.write(bytes((12,))) # write page delimiter (form feed 0x0C)
out.close()

Based on pdfplumber

import pdfplumber
import pandas as pd
# 读取pdf文件，保存为pdf实例
pdf =  pdfplumber.open("example.pdf") 
# 访问第二页
first_page = pdf.pages[1]
# 自动读取表格信息，返回列表
tables = first_page.extract_tables(table_settings = {
    
    })
for table in tables:
    table = pd.DataFrame(table[1:], columns=table[0])
    print(table)