从10中提取产品描述

Question

我想从一份10-k的报告中提取产品描述作为我的硕士论文（新的编程，财务背景）。此产品说明位于报告中的“项目1”和“项目2”之间。到目前为止，我所做的是下载所有10 ks in.txt格式，删除html标记，并使所有文本大写。我现在的问题是，当我试图选择我需要的文本并将其保存到另一个目录中时。我试着自己选，但结果不尽如人意。目前，我使用的是GitHub上一个叫“iammrhelo”的人编写的代码。他的代码是选择“第7项”到“第8项”。稍加调整，让它搜索我需要的东西。链接到他的代码：https://github.com/iammrhelo/edgar-10k-mda

我现在的问题是，他不适用于所有10 K。它适用于选择10k中的产品描述：

picture: 10k that the code is able to parse

picture: 10k that the code is NOT able to parse

为了提供一些上下文，我需要找到代码必须查找的正确语法。要查找的语法在列表item1\u begins中。 我用来选择文本的代码如下：

import argparse
import codecs
import os
import time
import re

from pathos.pools import ProcessPool
from pathos.helpers import cpu_count

class MDAParser(object):
    def __init__(self):
        pass

    def extract(self, txt_dir, mda_dir, parsing_log):
        self.txt_dir = txt_dir
        if not os.path.exists(txt_dir):
            os.makedirs(txt_dir)

        self.mda_dir = mda_dir
        if not os.path.exists(mda_dir):
            os.makedirs(mda_dir)

        def text_gen(txt_dir):
            # Yields markup & name
            for fname in os.listdir(txt_dir):
                if not fname.endswith('.txt'):
                    continue
                yield fname

        def parsing_job(fname):
            print("Parsing: {}".format(fname))

            # Read text
            filepath = os.path.join(self.txt_dir,fname)
            with codecs.open(filepath,'rb',encoding='utf-8') as fin:
                text = fin.read()

            name, ext = os.path.splitext(fname)
            # Parse MDA part

            msg = ""
            mda, end = self.parse_mda(text)
            # Parse second time if first parse results in index
            if mda and len(mda.encode('utf-8')) < 1000:
                mda, _ = self.parse_mda(text, start=end)

            if mda: # Has value
                msg = "SUCCESS"
                mda_path = os.path.join(self.mda_dir, name + '.txt')
                with codecs.open(mda_path,'w', encoding='utf-8') as fout:
                    fout.write(mda)
            else:
                msg = msg if mda else "MDA NOT FOUND"
            #print("{},{}".format(name,msg))
            return name + '.txt', msg #


        ncpus = cpu_count() if cpu_count() <= 8 else 8
        pool = ProcessPool( ncpus )

        _start = time.time()
        parsing_failed = pool.map( parsing_job, \
                                   text_gen(self.txt_dir) )
        _end = time.time()

        print("MDA parsing time taken: {} seconds.".format(_end-_start))

        # Write failed parsing list
        count = 0
        with open(parsing_log,'w') as fout:
            print("Writing parsing results to {}".format(parsing_log))
            for name, msg in parsing_failed:
                fout.write('{},{}\n'.format(name,msg))
                if msg != "SUCCESS":
                    count = count + 1

        print("Number of failed text:{}".format(count))

    def parse_mda(self, text, start=0):
        debug = False
        """
            Return Values
        """

        mda = ""
        end = 0

        """
            Parsing Rules
        """

        # Define start & end signal for parsing
        item1_begins = [ '\nITEM 1.', 'ITEM 1.' '\nITEM 1 –', '\nITEM 1:', '\nITEM 1 ', '\nITEM 1.\n', '\nITEM 1.\n']
        item1_ends   = [ '\nITEM 1A']
        if start != 0:
            item1_ends.append('\nITEM 1') # Case: ITEM 1A does not exist
        item2_begins = [ '\nITEM 2']

        """
            Parsing code section
        """
        text = text[start:]

        # Get begin
        for item1 in item1_begins:
            begin = text.find(item1)
            if debug:
                print(item1,begin)
            if begin != -1:
                break

        if begin != -1: # Begin found
            for item1A in item1_ends:
                end = text.find(item1A, begin+1)
                if debug:
                    print(item1A,end)
                if end != -1:
                    break

            if end == -1: # ITEM 7A does not exist
                for item2 in item2_begins:
                    end = text.find(item2, begin+1)
                    if debug:
                        print(item2,end)
                    if end != -1:
                        break

            # Get MDA
            if end > begin:
                mda = text[begin:end].strip()
            else:
                end = 0

        return mda, end

if __name__ == "__main__":
    parser = argparse.ArgumentParser("Parse MDA section of Edgar Form 10k")
    parser.add_argument('--txt_dir',type=str,default='C:/Users/Adrian PC/Desktop/Thesis stuff/10k abbot/python/10ktxt/')
    parser.add_argument('--mda_dir',type=str,default='./data/mda')
    parser.add_argument('--log_file',type=str,default='./parsing.log')
    args = parser.parse_args()

    # Extract MD&A from processed text
    # Note that the parser parses every text in the text_dir, not according to the index file
    parser = MDAParser()
    parser.extract(txt_dir=args.txt_dir, mda_dir=args.mda_dir, parsing_log=args.log_file)

Answer 1

如果我没听错的话，你需要在项目之间获取数据并将其放入一个列表中。在

您可以使用正则表达式https://docs.python.org/3.4/library/re.html。对文本的解析非常强大，我在那个脚本中看到它是导入的而不是使用的。在

如果要创建项目之间的数据列表，可以执行以下操作：

import re
item_symbol = re.compile('ITEM..\.') # creates the regular expression for the pattern 'ITEM #.' where # is the number
item_data = item_symbol.split(parsing_log) #splits the string into list items on the regular expression

示例：example