def txt2htmlGF(path=None,
m1=re.compile(r'^第\w{1,3}[编|篇]'),
m2=re.compile(r'^第\w{1,3}章'),
m3=re.compile(r'^第\w{1,3}节'),
ind=True,
regrex1=None,
search=None,
Startw=None):
"""
path:文件夹的名称,若没有输入参数，则默认为None，即当前目录。
func:txt2html_odir,形成一个个单独的文件，文件名与源文件相同，并保存在源文件的目录下。
:txt2htmlv1，合并成一个文件，文件保存在当前工作目录下，输出为output.html。
px: 按预先定义的方式进行排序
path:所选择的文件夹
"""
files = []
if isinstance(path, list):
files.extend(path)
elif os.path.isfile(path):
files.append(path)
elif path is None:
txtpath = os.getcwd()
ss = GFlist(path, regrex1=regrex1, research=search, startw=Startw)
files = [i[1] for i in ss]
elif os.path.isdir(path):
ss = GFlist(path, regrex1=regrex1, research=search, startw=Startw)
files = [i[1] for i in ss]
txt2htmlv1(files, m1=m1, m2=m2, m3=m3, index=ind)
return
def absfile(path,func=abssplit,regrex1=None,\
Research=None,Startw=None,p1=re.compile('裁判要点'),\
p2=re.compile('相关法条'),rc=re.compile('裁判要点\W*(.*?\s*.*?)\W*相关法条')):
files = []
if isinstance(path, list):
for i in path:
if os.path.isfile(i):
files.append(i)
elif os.path.isdir(i):
ss = GFlist(path,
regrex1=regrex1,
research=Research,
startw=Startw)
files.extend([i[1] for i in ss])
elif isinstance(path, str):
if os.path.isfile(path):
files.append(path)
elif path is None:
txtpath = os.getcwd()
ss = GFlist(path, regrex1=regrex1, research=Research, startw=Startw)
files.extend([i[1] for i in ss])
elif os.path.isdir(path):
ss = GFlist(path, regrex1=regrex1, research=Research, startw=Startw)
files.extend([i[1] for i in ss])
tdir = 'temp_dir'
if not os.path.exists(tdir):
os.mkdir(tdir)
Tfile = []
if func.__name__ == 'abstract':
for f in files:
bn = os.path.basename(f)
nf = os.path.join(tdir, bn)
text = func(f, rc=rc)
try:
with open(nf, 'w', encoding='utf8') as gf:
gf.write(text)
Tfile.append(nf)
except:
pass
elif func.__name__ == 'abssplit':
for f in files:
bn = os.path.basename(f)
nf = os.path.join(tdir, bn)
text = func(f, p1=p1, p2=p2)
#print(text)
try:
with open(nf, 'w', encoding='utf8') as gf:
gf.write(text)
Tfile.append(nf)
except:
pass
return Tfile
def absAPPhtml(path,
outdir='',
regrex1=re.compile('检例第(\d*)号'),
rc=re.compile('(.*?案\s*（检例第\d*号）)'),
p1=re.compile('【要旨】'),
p2=re.compile('\【\w*】'),
yz=True):
if outdir == '':
outdir = 'itempdit'
absSPP(path=path, tdir=outdir, rc=rc, p1=p1, p2=p2, yz=yz)
ss = GFlist(outdir, regrex1=regrex1)
Tfile = [i[1] for i in ss]
htmlcode = _hh(outdir)
tb, ctt = make_Mulu_content(Tfile)
htmlName = 'outputabsSPP.html'
try:
html = open(htmlName, 'w', encoding='utf8')
html.write(htmlcode)
html.write(tb)
html.write(ctt)
except:
html = open(htmlName, 'w', encoding='gbk')
html.write(htmlcode)
html.write(tb)
html.write(ctt)
html.write('</body></html>')
html.close()
shutil.rmtree(outdir)
return
return
def TopyhtmlGF(pf, regrex1=None, search=None, index=True, Startw=None):
pfname = pf.replace('/', '')
#print(pfname)
htmlf = pfname + '_content.html'
p = getcsspath()
ll = title + '\n' + title1 + ft % p + title2 + '\n'
if os.path.exists(htmlf):
os.remove(htmlf)
with open(htmlf, 'w', encoding='utf8') as f:
f.write(ll)
f.write('<div id="content"> \n')
f.write('<h1 class="title">%s</h1>\n<ul class="org-ul">\n' % pfname)
f.flush()
files = []
if isinstance(pf, list):
files.extend(pf)
elif pf is None:
txtpath = os.getcwd()
ss = GFlist(pf, regrex1=regrex1, research=search, startw=Startw)
files = [i[1] for i in ss]
elif os.path.isdir(pf):
ss = GFlist(pf, regrex1=regrex1, research=search, startw=Startw)
files = [i[1] for i in ss]
with open(htmlf, 'w', encoding='utf8') as f:
f.write(ll)
f.write('<div id="content"> \n')
f.write('<h1 class="title">%s</h1>\n<ul class="org-ul">\n' % pfname)
f.flush()
for ff in files:
name = os.path.splitext(os.path.basename(ff))[0]
#fpath=urllib.parse.quote(ff)
fpath = pathname2url(ff)
line = '<li><code>[ ]</code> <a href=%s>%s</a>\n</li>' % (fpath,
name)
try:
write_file(htmlf, line)
except Exception as e:
print(e)
write_file(htmlf, r"</ul>" + '\n')
write_file(htmlf, '</div>\n</body>\n</html>')
return
def C2html_AllinOneGF(txtpath=None,regrex1=None,Research=None,index=True,Startw=None,py=False):
"""
将目录txtpath下的txt文件内容全部转到output.html文件中
px:文中排序的基准。
"""
files=[]
if isinstance(txtpath,list):
files.extend(txtpath)
elif txtpath is None:
txtpath=os.getcwd()
ss=GFlist(txtpath,regrex1=regrex1,research=Research,startw=Startw)
files=[i[1] for i in ss]
elif os.path.isdir(txtpath):
ss=GFlist(txtpath,regrex1=regrex1,research=Research,startw=Startw)
files=[i[1] for i in ss]
C2html(files,index=index,py=py)
return
def absAPPhtml(path,outdir='',regrex1=re.compile('检例第(\d*)号'),\
rc=re.compile('(.*?案\s*（检例第\d*号）)'),\
p1=re.compile('【要\s*旨】'),\
p2=re.compile('【\w*】'),\
yz=True,func=C2html):
"""
主要是针对最高检察院的指导性案例，对每一个案例进行分类，或提取起裁判要旨
"""
if outdir == '':
outdir = 'itempdit'
absSPP(path=path, tdir=outdir, rc=rc, p1=p1, p2=p2, yz=yz)
ss = GFlist(outdir, regrex1=regrex1)
Tfile = [i[1] for i in ss]
if func.__name__ == 'C2html':
func(Tfile)
elif func.__name__ == "txt2htmlall":
func(Tfile, mformat='AIO')
shutil.rmtree(outdir)
return
def MainSpp(path,outdir='itempdit',regrex1=re.compile('检例第(\d*)号'),\
rc=re.compile('(.*?案\s*（检例第\d*号）)'),\
p1=re.compile('【要旨】'),p2=re.compile('\【\w*】'),\
yz=True,OutFile='MainSpp',mtype='pad',\
pyin=False,Total='max',item1_bool=False,item2_bool=False,\
item0_bool=False):
if outdir=='':
outdir='itempdit'
absSPP(path=path,tdir=outdir,rc=rc,p1=p1,p2=p2,yz=yz)
ss=GFlist(outdir,regrex1=regrex1)
txt_files={}
for i in ss:
txt_files[i[0]]=Singal_input(i[1],pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
if len(txt_files)>0:
txt_files1=sorted(txt_files.items(),key=lambda txt_files:txt_files[0])
else:
print('No files 适合条件')
sys.exit()
##########################3
if Total=='max':
OutFile1=OutFile+'.tex'
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in txt_files1:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
###########################3
elif isinstance(Total,int):
for f in txt_files1:
txp=[txt_files1[i:i+Total] for i in range(0,len(txt_files),Total)]
fn=1
for ff in txp:
OutFile1=OutFile+'_%s.tex'%str(fn).zfill(2)
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in ff:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
fn +=1
else:
print('Total is max out int, please input the right parameter.')
"""
for root,dirs,files in os.walk(tdir):
for f in files:
if os.path.splitext(f)[1] in ['.tex']:
os.remove('%s'%os.path.abspath(root+'/'+f))
pass"""
shutil.rmtree(outdir)
return
def MainsAbs(txtpath,func=abssplit,OutFile='Mainabs',mtype='pad',\
pyin=False,Total='max',regrex1=None,Research=None,\
Startw=None,rc=re.compile('\裁判要点\W*(.*?)\W*相关法条'),\
p1=re.compile('裁判要点'),p2=re.compile('相关法条'),\
item1_bool=False,item2_bool=False,\
item0_bool=False):
txt_files={}
rsch=[]
if isinstance(Research,str):
rsch.append(Research)
elif isinstance(Research,list):
rsch.extend(Research)
files=[]
if isinstance(txtpath,list):
files.extend(txtpath)
elif txtpath is None:
txtpath=os.getcwd()
ss=GFlist(txtpath,regrex1=regrex1,research=Research,startw=Startw)
files=[i[1] for i in ss]
elif os.path.isdir(txtpath):
ss=GFlist(txtpath,regrex1=regrex1,research=Research,startw=Startw)
files=[i[1] for i in ss]
tdir='temp_dir'
if not os.path.exists(tdir):
os.mkdir(tdir)
for f in files:
print(f)
if func.__name__=='abstract':
bn=os.path.basename(f)
nf=os.path.join(tdir,bn)
#print(nf)
try:
text=func(f,rc=rc)
#print(text)
with open(nf,'w',encoding='utf8') as gf:
gf.write(text)
#Tfile.append(f[0],nf)
except:
print('没有相应的内容for abstract')
pass
elif func.__name__=='abssplit':
bn=os.path.basename(f)
nf=os.path.join(tdir,bn)
try:
text=func(f,p1=p1,p2=p2)
#print(text)
with open(nf,'w',encoding='utf8') as gf:
gf.write(text)
#Tfile[f[0]]=nf
#Tfile.append(f[0],nf)
except:
print('没有相应的内容for abssplit')
pass
ss=GFlist(tdir,regrex1=regrex1)
for i in ss:
txt_files[i[0]]=Singal_input(i[1],pyin,item1_bool=item1_bool,item2_bool=item2_bool,item0_bool=item0_bool)
if len(txt_files)>0:
txt_files1=sorted(txt_files.items(),key=lambda txt_files:txt_files[0])
else:
print('No files 适合条件')
sys.exit()
##########################3
if Total=='max':
OutFile1=OutFile+'.tex'
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in txt_files1:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
###########################3
elif isinstance(Total,int):
for f in txt_files1:
txp=[txt_files1[i:i+Total] for i in range(0,len(txt_files),Total)]
fn=1
for ff in txp:
OutFile1=OutFile+'_%s.tex'%str(fn).zfill(2)
fl=open(OutFile1,'w',encoding='utf8')
fl.write(latexs[mtype]+'\n\n')
for f in ff:
fl.write('\input{%s}'%f[1])
fl.write(r'\newpage')
#fl.write('\n\n')
fl.write(end)
fl.close()
os.system('xelatex -no-pdf -interaction=nonstopmode %s' %OutFile1)
os.system('xelatex -interaction=nonstopmode %s' %OutFile1)
_removef(OutFile1)
fn +=1
else:
print('Total is max out int, please input the right parameter.')
"""
for root,dirs,files in os.walk(tdir):
for f in files:
if os.path.splitext(f)[1] in ['.tex']:
os.remove('%s'%os.path.abspath(root+'/'+f))
pass"""
shutil.rmtree(tdir)
return
def GenerateBookGF(path,regrex1=None,\
search=None,startw=None,\
exclude=None,\
func=C2html,\
item1_bool=False,\
item2_bool=False,\
item0_bool=False,\
htmlfile='htmlfile/htmlbook_output',\
pdffile='htmlbook_Main',mtype='article',\
num=None,pyin=False,File_num='max',\
m1=re.compile(r'^第\w{1,3}[编|篇]'),\
m2=re.compile(r'^第\w{1,3}章'),\
m3=re.compile(r'^第\w{1,3}节'),\
m4=re.compile(r'^\w{1,3}、'),\
index=True,res=True,\
Spp=False,\
Spplit=False,\
rc=re.compile('(.*?案\s*（检例第\d*号）)'),\
p1=re.compile('【要\s*旨】'),p2=re.compile('【\w*】'),yz=True):
"""
regrex:re.compile('\d*'),从文件名中提取中关键字作排序用
search:str/list,民事诉讼，将文件名中符合含有关键字的文件提取出来
startw:re.compile('^ok')，将文件名中以特定字开头的文件提取出来
exclude:str/list,刑事诉讼，将含有exclude的文件予以排除
num:regrex的作用相同，主要是用于latex的文件中
m1:html文件中的一级目录
m2:同上，是2级目录g
m3:同上,是3级目录
m4:同上，是4级目录
"""
if func.__name__ in ['MainSpp']:
func(path,yz=yz,mtype=mtype)
return
if func.__name__ in ['MainsAbs']:
func(path,pyin=pyin,Startw=startw,mtype=mtype,regrex1=regrex1)
return
cc=re.compile('([，、:-》.《—_;；〈〉<>【】（）()])*\s*-')
rs=[]
if isinstance(search ,list):
rs.extend(search)
elif isinstance(search ,str):
rs.append(search)
excl=[]
if isinstance(exclude ,list):
excl.extend(exclude)
elif isinstance(exclude,str):
excl.append(exclude)
file_list = []
path_list = []
if isinstance(path,list):
for f in path:
if isfile(f):
file_list.append(f)
elif isdir(f):
path_list.append(f)
elif isfile(path):
file_list.append(path)
elif isdir(path):
path_list.append(path)
elif path is None:
txtpath = os.getcwd()
else:
print('Please in list of dir/file,or dir,file')
sys.exit()
File_tmp = GFlist(path_list)
for ff in File_tmp:
file_list.append(ff[1])
only_one = set()
fls = []
word = re.compile(r'[\u4e00-\u9fa5]+\d*')
for ff in file_list:
aa = os.path.basename(ff)
nwd = ''.join(word.findall(aa))
if nwd not in only_one:
only_one.add(nwd)
fls.append(ff)
if len(fls) > 0:
file_list = fls
temff = set()
if exclude is not None:
for ff in file_list:
for ex in excl:
if ex in os.path.basename(ff):
temff.add(ff)
File_tmp = [f for f in file_list if f not in temff]
Final_list = {}
for f in File_tmp:
ff=basename(f)
if regrex1 is not None:
if splitext(ff)[1].lower() in ['.txt','.doc','.docx']:
i1 = [i for i in regrex1.findall(ff) if len(i) > 0]
i2 = [i for i in regrex1.findall(ut.ChNumToArab(ff)) if len(i) > 0]
if len(i1) > 0:
num1 = int(i1[0])
Final_list[num1] = f
elif len(i2) > 0:
num1= int(i2[0])
Final_list[num1] = f
else:
num1 = cc.sub('', ff).replace(' ', '')
Final_list[num1] = f
if search is not None:
Tem={}
for k,v in Final_list.items():
for rsch in rs:
if rsch in basename(v):
Tem[k]=v
if len(Tem)>0:
Final_list=Tem
else:
print('没有关于 "%s" 的文件'%search)
sys.exit()
if startw is not None:
dff={}
for k,v in Final_list.items():
if startw.match(basename(v)) is not None:
#print('start word ...',v)
dff[k]=v
if len(dff)>0:
Final_list=dff
else:
print('没有符合的文件')
sys.exit()
if len(Final_list)>0:
Final=sorted(Final_list.items(),key=lambda item:item[0],reverse=res)
Final_files=[i[1] for i in Final]
#if res:
# Final_files
if func.__name__ in ['C2html','txt2htmlv1']:
func(Final_files,output=htmlfile,m1=m1,m2=m2,m3=m3,index=index)
pass
elif func.__name__ in ['PdfFile']:
func(Final_files,OutFile=pdffile,mtype=mtype,\
num=num,pyin=pyin,Total=File_num,\
item0_bool=item0_bool,\
item1_bool=item1_bool,item2_bool=item2_bool)
#os.remove(pdffile+'.pdf','htmlfile/'+pdffile+'.pdf')
pass
else:
print('Please input right function:','C2html','C2htmlBase','txt2htmlv1','txt2html_inonefile','PdfFile')
if Spplit:
shutil.rmtree(path)
return#Final_files
def TopyhtmlGF(pf, regrex1=None, search=None, index=True, Startw=None):
#print(pf)
if isinstance(pf, str):
pfname = pf.replace('/', '_')
elif isinstance(pf, list):
pfname = 'selectdirs'
elif pf is None:
pfname = 'selectdirs'
else:
raise Exception('请输入文件目录')
htmlf = pfname + '_content.html'
p = getcsspath()
ll = title + '\n' + title1 + ft % p + title2 + '\n'
if os.path.exists(htmlf):
os.remove(htmlf)
files = []
#print('test 1')
if pf is None:
pf = os.getcwd()
ss = GFlist(pf, regrex1=regrex1, research=search, startw=Startw)
files.extend([i[1] for i in ss])
elif isinstance(pf, list):
for ff in pf:
if os.path.isdir(ff):
files.append(ff)
print(ff)
ss = GFlist(ff,
regrex1=regrex1,
research=search,
startw=Startw)
files.extend([i[1] for i in ss])
elif os.path.isfile(ff):
files.append(ff)
elif isinstance(pf, str):
if not os.path.exists(pf):
raise Exception('文件不存在,请输入正确的文件或目录')
#sys.exit()
if os.path.isdir(pf):
ss = GFlist(pf, regrex1=regrex1, research=search, startw=Startw)
files.extend([i[1] for i in ss])
elif os.path.isfile(pf):
files.append(pf)
with open(htmlf, 'w', encoding='utf8') as f:
f.write(ll)
f.write('<div id="content"> \n')
f.write('<h1 class="title">%s</h1>\n<ul class="org-ul">\n' % pfname)
f.flush()
ss = set()
#print(files)
for ff in files:
if os.path.isfile(ff):
dn = os.path.dirname(ff)
if dn not in ss:
ss.add(dn)
rname = os.path.split(dn)[1]
dline = '\n<li>- d  <a href=%s>%s</a> \n</li>\n' % (
pathname2url(os.path.abspath(dn)), rname)
write_file(htmlf, dline)
name = os.path.splitext(os.path.basename(ff))[0]
fpath = pathname2url(os.path.abspath(ff))
line = '<ul> - <code>[ ]</code> <a href=%s>%s</a>\n</ul>' % (
fpath, name)
try:
write_file(htmlf, line)
except Exception as e:
print(e)
write_file(htmlf, r"</ul>" + '\n')
write_file(htmlf, '</div>\n</body>\n</html>')
return
def absTFilehtml(txtpath,
func=abssplit,
rc=re.compile('裁判要点\W*(.*?\s*.*?)\W*相关法条'),
p1=re.compile('裁判要点'),
p2=re.compile('相关法条'),
regrex1=None,
Research=None,
index=True,
Startw=None,
m1=re.compile(r'^第\w{1,3}[编|篇]'),
m2=re.compile(r'^第\w{1,3}章'),
m3=re.compile(r'^第\w{1,3}节')):
"""
rc:需要提取的主要内容
regrex1:
"""
files = []
if isinstance(txtpath, list):
files.extend(txtpath)
elif txtpath is None:
txtpath = os.getcwd()
ss = GFlist(txtpath, regrex1=regrex1, research=Research, startw=Startw)
files = [i[1] for i in ss]
elif os.path.isdir(txtpath):
ss = GFlist(txtpath, regrex1=regrex1, research=Research, startw=Startw)
files = [i[1] for i in ss]
tdir = 'temp_dir'
if not os.path.exists(tdir):
os.mkdir(tdir)
htmlcode = _hh(txtpath)
Tfile = []
if func.__name__ == 'abstract':
for f in files:
bn = os.path.basename(f)
nf = os.path.join(tdir, bn)
text = func(f, rc=rc)
try:
with open(nf, 'w', encoding='utf8') as gf:
gf.write(text)
Tfile.append(nf)
except:
pass
elif func.__name__ == 'abssplit':
for f in files:
bn = os.path.basename(f)
nf = os.path.join(tdir, bn)
text = func(f, p1=p1, p2=p2)
#print(text)
try:
with open(nf, 'w', encoding='utf8') as gf:
gf.write(text)
Tfile.append(nf)
except:
pass
tb, ctt = make_Mulu_content(Tfile, m1=m1, m2=m2, m3=m3, index=index)
htmlName = 'outputabs.html'
try:
html = open(htmlName, 'w', encoding='utf8')
html.write(htmlcode)
html.write(tb)
html.write(ctt)
except:
html = open(htmlName, 'w', encoding='gbk')
html.write(htmlcode)
html.write(tb)
html.write(ctt)
html.write('</body></html>')
html.close()
shutil.rmtree(tdir)
return
def absTFilehtml(txtpath,func=abssplit,\
rc=re.compile('裁判要点\W*(.*?\s*.*?)\W*相关法条'),\
p1=re.compile('裁判要点'),p2=re.compile('相关法条'),\
regrex1=None,Research=None,index=True,Startw=None,\
m1=re.compile(r'^第\w{1,3}[编|篇]'),\
m2=re.compile(r'^第\w{1,3}章'),\
m3=re.compile(r'^第\w{1,3}节'),\
thtmlfunc=C2html):
"""
主要是针对最高法的指导性案例，提取起裁判要旨
rc:需要提取的主要内容
regrex1:
"""
files = []
if isinstance(txtpath, list):
files.extend(txtpath)
elif txtpath is None:
txtpath = os.getcwd()
ss = GFlist(txtpath, regrex1=regrex1, research=Research, startw=Startw)
files = [i[1] for i in ss]
elif os.path.isdir(txtpath):
ss = GFlist(txtpath, regrex1=regrex1, research=Research, startw=Startw)
files = [i[1] for i in ss]
tdir = 'temp_dir'
if not os.path.exists(tdir):
os.mkdir(tdir)
htmlcode = _hh(txtpath)
Tfile = []
if func.__name__ == 'abstract':
for f in files:
bn = os.path.basename(f)
nf = os.path.join(tdir, bn)
text = func(f, rc=rc)
try:
with open(nf, 'w', encoding='utf8') as gf:
gf.write(text)
Tfile.append(nf)
except:
pass
elif func.__name__ == 'abssplit':
for f in files:
bn = os.path.basename(f)
nf = os.path.join(tdir, bn)
text = func(f, p1=p1, p2=p2)
#print(text)
try:
with open(nf, 'w', encoding='utf8') as gf:
gf.write(text)
Tfile.append(nf)
except:
pass
ss = GFlist(tdir, regrex1=regrex1, research=Research, startw=Startw)
if thtmlfunc.__name__ == 'C2html':
thtmlfunc(Tfile)
elif thtmlfunc.__name__ == "txt2htmlall":
thtmlfunc(Tfile, mformat='AIO')
#shutil.rmtree(tdir)
return
