伤寒论阳明篇(python文本搜索)

# //    ? 与 {0,1}:0个或1个前面的内容 或 前面的内容是可选的
# //    * 与 {0,} : 0 个或多个前面的内容
# //    + 与 {1,}: 1 个或多个前面的内容
import re
import requests
from lxml import etree
from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait

wpath='/home/jl73/7-tmp/ag687/'
fileName='2阳明'
fileName2='2阳明2'
fileNameAddLine='addLineNum'

# strSelet=['三|火','温','之','气']
strSelet=['三|火','温','之']
lineNumList=[]

def mtRe(str,line):
    pat = re.compile(str)
    fin = re.findall(pat, line)
    return fin

def mtAddLineNum():
    baseNum = 1
    with open(wpath + fileNameAddLine, 'r', encoding='utf-8') as rag:
        lines = rag.readlines()
        for line in lines:
            str1 = r'【(\d+)】(.*)'
            fin = mtRe(str1,line)
            # print(fin)
            if fin != []:
                newLine = '【' + fin[0][0] + ' Line' + str(baseNum) + '】' + fin[0][1]
                print(newLine)
            baseNum=baseNum+1

def mt2():
    with open(wpath + fileName, 'r', encoding='utf-8') as rag:
        with open(wpath + fileName2, 'w', encoding='utf-8') as wag:
            lines = rag.readlines()
            for line in lines:
                # pat0 = re.compile(r'^([0-9]+)(.*)')
                pat0 = re.compile(r'\d+.\d+ Line.*')
                # pat0 = re.compile(r'^(\d+)(.*)')
                fin = re.findall(pat0, line)
                if fin!=[]: