深入探索Python如何利用pdfplumber从PDF中提取信息到实际项目应用

pip install pdfplumber

import pdfplumber

# 读取PDF文档
with pdfplumber.open('example.pdf') as pdf:
    # 获取文档的总页数
    total_pages = len(pdf.pages)

    # 遍历每一页
    for page_number in range(total_pages):
        # 获取当前页
        page = pdf.pages[page_number]

        # 提取文本内容
        text = page.extract_text()

        # 打印文本内容
        print(f"Page {page_number + 1}:\n{text}")

import pdfplumber
import pandas as pd

# 读取PDF文档
with pdfplumber.open('example.pdf') as pdf:
    # 获取文档的总页数
    total_pages = len(pdf.pages)

    # 创建一个空的DataFrame来存储表格数据
    df = pd.DataFrame()

    # 遍历每一页
    for page_number in range(total_pages):
        # 获取当前页
        page = pdf.pages[page_number]

        # 提取表格数据
        table = page.extract_table()

        # 将表格数据转换为DataFrame
        df_page = pd.DataFrame(table)

        # 将当前页的数据添加到整体DataFrame中
        df = df.append(df_page, ignore_index=True)

    # 将DataFrame写入Excel文件
    df.to_excel('output.xlsx', index=False)

import pdfplumber
import pandas as pd

with pdfplumber.open('example.pdf') as pdf:
    total_pages = len(pdf.pages)
    df = pd.DataFrame()
    for page_number in range(total_pages):
        page = pdf.pages[page_number]
        # ...

table = page.extract_table()
df_page = pd.DataFrame(table)

df = df.append(df_page, ignore_index=True)

df.to_excel('output.xlsx', index=False)

import pdfplumber
import re

def extract_information_from_pdf(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        total_pages = len(pdf.pages)

        # 创建一个空的列表用于存储信息
        extracted_data = []

        for page_number in range(total_pages):
            page = pdf.pages[page_number]

            # 提取文本内容
            text = page.extract_text()

            # 使用正则表达式提取姓名、邮箱地址和电话号码
            name_match = re.search(r'姓名: (.+)', text)
            email_match = re.search(r'邮箱: (.+)', text)
            phone_match = re.search(r'电话: (.+)', text)

            if name_match and email_match and phone_match:
                name = name_match.group(1)
                email = email_match.group(1)
                phone = phone_match.group(1)

                # 将提取的信息添加到列表中
                extracted_data.append({'姓名': name, '邮箱': email, '电话': phone})

    return extracted_data

# 指定PDF文件路径
pdf_file_path = 'person_info.pdf'

# 提取信息并打印
result = extract_information_from_pdf(pdf_file_path)
for entry in result:
    print(entry)

import pdfplumber
import re

def extract_information_from_text(text):
    name_match = re.search(r'姓名: (.+)', text)
    email_match = re.search(r'邮箱: (.+)', text)
    phone_match = re.search(r'电话: (.+)', text)

    if name_match and email_match and phone_match:
        name = name_match.group(1)
        email = email_match.group(1)
        phone = phone_match.group(1)
        return {'姓名': name, '邮箱': email, '电话': phone}
    else:
        return None

def extract_information_from_pdf(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        total_pages = len(pdf.pages)
        extracted_data = []

        for page_number in range(total_pages):
            page = pdf.pages[page_number]
            text = page.extract_text()
            
            result = extract_information_from_text(text)
            if result:
                extracted_data.append(result)

    return extracted_data

def extract_information_from_pdf(pdf_path):
    with pdfplumber.open(pdf_path) as pdf:
        total_pages = len(pdf.pages)
        extracted_data = []

        for page_number in range(total_pages):
            try:
                page = pdf.pages[page_number]
                text = page.extract_text()

                result = extract_information_from_text(text)
                if result:
                    extracted_data.append(result)
            except Exception as e:
                print(f"Error processing page {page_number + 1}: {str(e)}")

    return extracted_data