如何使用Python for NLP将PDF文件转换为可搜索的文本？

pip install pdfplumber

pip install nltk
pip install spacy

import pdfplumber

with pdfplumber.open('input.pdf') as pdf:
    pages = pdf.pages

text = ""
for page in pages:
    text += page.extract_text()

# 可以在这里进行一些文本预处理，如去除特殊字符、标点符号、数字等。这里仅提供一个简单示例：
import re

text = re.sub(r'[^a-zA-Zs]', '', text)

import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

# 下载所需的nltk数据
nltk.download('stopwords')
nltk.download('punkt')
nltk.download('wordnet')

# 初始化停用词、词形还原器和标记器
stop_words = set(stopwords.words('english'))
lemmatizer = WordNetLemmatizer()
tokenizer = nltk.RegexpTokenizer(r'w+')

# 进行词形还原和标记化
tokens = tokenizer.tokenize(text.lower())
lemmatized_tokens = [lemmatizer.lemmatize(token) for token in tokens]

# 去除停用词
filtered_tokens = [token for token in lemmatized_tokens if token not in stop_words]

# 将结果保存到文件
with open('output.txt', 'w') as file:
    file.write(' '.join(filtered_tokens))