在这里，我使用 python 从本地存储的 html 文件中提取圣经经文，实际上这个 python 不是我写的，我从某个地方得到的，当我运行 python 代码来提取圣经经文时，我得到类似这种类型的东西，u'Joseph asopo atum aphan Jakob thek-longsi, alangli arjulo, \u201cLahei komat asomarlo?\u201d'它有很多行这种类型，在写入文件时无法正确编码 unicode 字符。在终端上运行时，它可以正确显示并正确编码 unicode 字符。如果有人可以纠正问题，这里是 python 代码，这里是本地存储的 html下载 zip 格式的 html 文件 这是Python文件。此Python代码正在读取文件夹下的html文件example并在文件夹内生成输出文件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)
这是一些输出文件的屏幕截图
