여기에서는 Python을 사용하여 로컬에 저장된 HTML 파일에서 성경 구절을 추출하고 있습니다. 실제로 이 Python은 제가 작성한 것이 아니며 어딘가에서 가져온 것입니다. 성경 구절을 추출하기 위해 Python 코드를 실행할 때 다음과 같은 결과가 나타납니다. u'Joseph asopo atum aphan Jakob thek-longsi, alangli arjulo, \u201cLahei komat asomarlo?\u201d'이러한 유형의 줄이 많은 것은 파일에 쓸 때 유니코드 문자를 올바르게 인코딩하지 않습니다. 터미널에서 실행하면 유니코드 문자가 올바르게 표시되고 인코딩됩니다. 누구든지 문제를 해결할 수 있다면 여기에 Python 코드가 있고 여기에 로컬로 저장된 HTML이 있습니다.zip 형식의 html 파일 다운로드 이것은파이썬 파일. 이 Python 코드는 폴더 아래의 HTML 파일을 읽고 example폴더 내에 출력 파일을 생성합니다.example/exampleoutputs
import os, sys
import numpy as np
import array as arr
import re
from lxml import etree
from lxml import html
import urllib2
from bs4 import BeautifulSoup
import csv
import codecs
import shutil
class BIBLE_CLASS:
def __init__(self,path):
self.bookslist=[]
def readBookList(self,path): # Read the data from file
file=open(path,'r')
for x in file:
# print(x)
self.bookslist.append(x)
#print(Bookslist)
#for i in range(1,len(self.bookslist)):
# print(self.bookslist[i])
def searchBook(self,book): # Search the book ID in the books file
#bookcode=0
for i in range(1,len(self.bookslist)):
st=str(self.bookslist[i])
#st=st.upper()
#skey=book.upper()
#print(st,'',skey)
if(st.find(book)!=-1):
temp=self.bookslist[i]
index1=temp.index(',')
#print(temp[0:index1])
bookcode=temp[0:index1]
#print(bookcode)
return bookcode
def writeStoryFile(self,path):
# Writes data into story file
filext1=['.html']
print("writeStoryFile")
dirs=os.listdir(path)
pattern=re.compile("^v")
# CREATE A FOLDER WITH PATH+OUTPUTS AS NAME
outputfile=path+"outputs"
outpath=os.path.join(path,outputfile)
if os.path.exists(outpath):
shutil.rmtree(outpath)
else:
os.mkdir(outpath)
for d in dirs: #For each directory extract stories from files
print("Directory name:",d)
btitle=d[d.rindex('_')+1:]
print(btitle)
print('Book code:',o1.searchBook(btitle)) # Book code is extracted
fullpath=os.path.join(path,d)
if os.path.isdir(fullpath):
print("Converting folder",fullpath)
files=os.listdir(fullpath)
rno=0
# GET THE BOOK CODE FROM THE FILE
btitle=d[d.rindex('_')+1:]
#print(btitle)
#print('Book code:',o1.searchBook(btitle))
bcode=o1.searchBook(btitle)
print(bcode)
# CREATE STORY LINE FILE FOR EACH FOLDER
csvfile1=outpath+"/"+d+"story.csv" # story line filename
f1 = codecs.open(csvfile1, encoding='utf-8',mode='w') # Creating story lines file
csvfile2=outpath+"/"+d+"storyverses.csv" # story line with verses files
csvfile3=outpath+"/"+d+"veses.csv" # only verses
f2 = codecs.open(csvfile2, encoding='utf-8',mode='w')
f3=codecs.open(csvfile3, encoding='utf-8',mode='w')
for f in files:
fname,fext=os.path.splitext(f)
rows=[]
if fext in filext1:
print("=================Processing the file",f,"========================")
# Process the file
print "Stories in the chapter:"
# fullpath=os.path.join(path,file)
wpath=os.path.join(fullpath,f)
text=open(wpath,"r")
# csvfile1=wpath.replace('.html','story.csv') # story line filename
html_doc=text.read()
soup = BeautifulSoup(html_doc, 'html.parser',from_encoding="utf-8")
h3s = soup.find_all('h3')
storyverses=[]
storytitles=[]
for h3 in h3s:
next_element = h3.find_next()
print next_element.text
if next_element.find('sup') is None:
print("Element is null")
required_element=next_element.find_next()
if required_element is None:
required_element=next_element.next_element.find_next()
if required_element.find('sup') is None:
break
required_element= required_element.find_next('sup')
superscript_number = str(required_element.find_next('sup').text)
# print bcode,fname,superscript_number,h3.text
print "========",superscript_number
if len(superscript_number)>2:
storyverses.append(int(superscript_number[0:1]))
sn=superscript_number[0:1]
print sn
st=int(bcode),int(fname),int(superscript_number[0:1]), str(h3.text)
else:
storyverses.append(int(superscript_number))
st=int(bcode),int(fname),int(superscript_number), (h3.text).encode('utf-8')
storytitles.append(h3.text)
print st
rows.append(st)
rno=rno+1
else:
superscript_number = str(next_element.find('sup').text)
if len(superscript_number)>2:
storyverses.append(int(superscript_number[0:1]))
sn=superscript_number[0:1]
print sn
st=int(bcode),int(fname),int(superscript_number[0:1]), str(h3.text)
else:
storyverses.append(int(superscript_number))
st=int(bcode),int(fname),int(superscript_number), str(h3.text)
storytitles.append(h3.text)
print st
rows.append(st)
rno=rno+1
#print storytitles[0]
# Write story lines into file
# f1 = codecs.open(csvfile1, encoding='utf-8',mode='w') # Creating story lines file
for row in rows:
f1.write(str(row))
f1.write("\n")
# csvfile2=wpath.replace('.html','verse.csv') # story line files
# csvfile3=wpath.replace('.html','veses.csv')
# f2=open(csvfile2,"w")
verses=[]
verseno=1
# f2 = codecs.open(csvfile2, encoding='utf-8',mode='w')
# f3=codecs.open(csvfile3, encoding='utf-8',mode='w')
#f2=codecs.open(csvfile2,mode='w')
#f3=codecs.open(csvfile3,mode='w')
print "======================================================================================"
k=0
for y in soup.findAll('span',class_=[pattern,"heading"]):
sups=y('sup')
for z in sups:
z.decompose()
if verseno in storyverses:
st1=str(rows[storyverses.index(verseno)])
k=k+1
f2.write(st1)
f2.write("\n")
verses.append(st1)
print bcode,fname, verseno,'"'+y.text+'"'
st=int(bcode),int(fname), verseno,y.text
f2.write(str(st))
f2.write("\n")
f3.write(str(st))
f3.write("\n")
verses.append(st)
# print st
else:
print bcode,fname, verseno,'"'+y.text+'"'
st=int(bcode),int(fname),verseno,y.text
f2.write(str(st))
f2.write("\n")
f3.write(str(st))
f3.write("\n")
verses.append(st)
verseno+=1
# f1.close()
# f2.close()
# f3.close()
def writeVerses(self):
print("writeVerses")
# Writes verses into verse file
def writebothVerse(self):
print("writeStoryFile")
# Writes verse with story in between
# Main program
bookspath="BookCode/books.csv"
path='example' # Change this to the actual path of the input data
o1=BIBLE_CLASS(path)
# Step 1: Read the book list from the file
o1.readBookList(bookspath)
# Step 2: Create story files
o1.writeStoryFile(path)
filext1=['.html']
dirs=os.listdir(path)
다음은 출력 파일의 일부 스크린샷입니다.
