docxconvert/parsedocx.py

#-*-coding:utf-8 -*-
import bs4
import re,os
import json,uuid
from bs4 import BeautifulSoup
import threading 
import shutil
import pprint
class QuestionsParser(object):
    """试题解析
    """
    def __init__(self,name="lasttest001.html"):
        self.html = open(name,"r").read()
        self.soup = BeautifulSoup(self.html,"html.parser")

    def get_paragraphs(self):
        """
        """
        data = []
        wordsection = self.soup.find_all("g",attrs={"xml:space":"preserve"})
        for svg in wordsection:
            pars = svg.find_all("g")
            for par in pars:
                if isinstance(par,bs4.element.Tag):
                    if par.find("path") and len(list(par.children))<=2:
                        data.append(par)
                    else:
                        data.extend(list(par.children))
        return data

    def parse_questions(self):
        """提取试题
        """
        data = []
        tmp_val = {"tx":""}
        tx_name = ""
        key = ""
        paragraphs = self.get_paragraphs()

        label = ""
        tx_label = ""
        tg_label = ""
        zsd_label = ""
        nd_label = ""
        da_label = ""
        jx_label = ""
        for i,p in enumerate(paragraphs):
            if not isinstance(p,bs4.element.NavigableString):
                #print(label)
                if u"【题型】" in label:
                    key = "tx"
                if u"【题干】" == label:
                    key = "tg"
                    if tmp_val.get("tg") and tmp_val.get("da"):
                        data.append(tmp_val)
                    tmp_val = {"tg":"","tx":"","zsd":"","nd":"","da":"","jx":""}

                if u"【知识点】" in label:
                    key = "zsd"
                if u"【难度】" in label:
                    key = "nd"
                if u"【答案】" in label:
                    key = "da"
                if u"【解析】" in label:
                    key = "jx"

                if key != "":
                    if u"【" not in p.text:
                        if key == "tx" and u"【题型】" in label:
                            tmp_val[key] += p.text.replace("\n","")
                        if key == "tg" and u"【题干】" in label:
                            tmp_val[key] += p.__str__()
                        if key == "zsd" and u"【知识点】" in label:
                            tmp_val[key] += p.__str__()
                        if key == "nd" and u"【难度】" in label:
                            tmp_val[key] += p.__str__()
                        if key == "da" and u"【答案】" in label:
                            tmp_val[key] += p.__str__()
                        if key == "jx" and u"【解析】" in label:
                            tmp_val[key] += p.__str__()

                if u"【" in p.text:
                    label = ""
                    label += p.text.replace("\n","")
                elif u"】" in p.text:
                    label += p.text.replace("\n","")
                else:
                    label += p.text.replace("\n","")

        data.append(tmp_val)
        return data

    def get_questions(self):
        """
        """
        svgstart = '<svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:svg="http://www.w3.org/2000/svg" width="100%" height="180px" viewBox="40 180 900 90" xml:space="preserve"><g xml:space="preserve">'
        svgend = '</g></svg>'
        questions = self.parse_questions()
        for i,que in enumerate(questions):
            if que:
                que['tg'] = svgstart + que['tg'] + svgend
                que['jx'] = svgstart + que['jx'] + svgend
                que['zsd'] = svgstart + que['zsd'] + svgend
                que['da'] = svgstart + que['da'] + svgend
                que['nd'] = svgstart + que['da'] + svgend
                que['qno'] = str(i)
        #for que in questions:
        #    if que:
        #        #que["tx"] = que["tx"].split(u"、")[-1]
        #        #que["tg"] = que["tg"].replace(u"【题干】","")
        #        #que["zsd"] = que["zsd"].replace(u"【知识点】","")
        #        #que["da"] = que["da"].replace(u"【答案】","")
        #        #que["jx"] = que["jx"].replace(u"【解析】","")
        #        #que["qno"] = self.get_qno(que["tg"])
        return questions

    def get_qno(self,tg):
        """提取题号
        """
        tgsoup = BeautifulSoup(tg,"html.parser")
        tgtext = tgsoup.text
        qno = re.search(r"\d+",tgtext.split(u"、")[0]).group()
        return qno
        


if __name__ == "__main__":
    questionparser =  QuestionsParser("C:\\AppData\\say365\\htmp\\ecb6c73b-78dc-4b66-83a0-ebf3803645b8.html")
    ques = questionparser.get_questions()
    for que in ques:
        if que:
            print("*"*100)
            print(que["tg"])
            pass
        #break