解析pdf的一些尝试

• 使用pdfplumber

import pdfplumber
from itertools import pairwise


class Document:
    def __init__(self, filename):
        self.pdf = pdfplumber.open(filename)

    def get_all_words(self):
        for page in self.pdf.pages:
            for word in page.extract_words():
                yield word["text"]

    def get_joined_tokens(self):
        for i, j in pairwise(self.get_all_words()):
            yield i + j

    def get_critical(self):
        for token in self.get_joined_tokens():
            if "信息技术" in token and "投入" in token:
                print(f"\n {token} \n")