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 C2htmlBase(txtpath,output='outputbase.html',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,py=False):
"""
txtpath:为单独的文件或一段字符
"""
p=getcsspath()
ft='''\n<link rel="stylesheet" type="text/css" href="%s" />'''
ll=title+'\n'+title1+ft%p+title2+'\n'
#print(ll)
files=[]
if os.path.isfile(txtpath):
if os.path.splitext(txtpath)[1].lower() in ['.txt','.doc','.docx']:
files.append(txtpath)
#tname=os.path.splitext(os.path.basename(txtpath))[0]
elif isinstance(txtpath,str):
path123='tempsdfsf.txt'
fff=open(path123,'w',encoding='utf8')
fff.write(txtpath)
fff.close()
files.append(path123)
else:
print('Please input a file for txt,doc,or strings')
sys.exit()
tb,ctt=make_Mulu_content(files,m1=m1,m2=m2,m3=m3,index=index,py=py)
if os.path.exists(output):
os.remove(output)
try:
if os.path.exists(path123):
os.remove(path123)
except:
pass
try:
html=open(output,'a',encoding='utf8')
html.write(ll)
#html.write('<div id="content">\n')
html.write('<div id="content",style="background-color:#C7EDF0">\n')
html.write(tb)
html.write(ctt)
except:
html=open(output,'a',encoding='gbk')
html.write(ll)
#html.write('<div id="content">\n')
html.write('<div id="content",style="background-color:#C7EDF0">\n')
html.write(tb)
html.write(ctt)
html.write(endd)
html.close()
print("\n转换成功,保存在%s"%output)
return
def txt2htmlv1(txtName,
output="outputtxt",
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'),
index=True,
py=False):
"""
txtName:文件的名称（含所在的文件夹）
index： True,将第四节的列入目录
False,不含第四节的目录
---------------
在python运行目录下生产一份html文件。
"""
files = []
htmlcode1 = _hh(txtName)
if isinstance(txtName, str):
files.append(txtName)
elif isinstance(txtName, list):
files.extend(txtName)
if output == '':
htmlName = "outputtxt.html"
else:
output = output + '.html'
htmlName = output
tb, ctt = make_Mulu_content(files, m1=m1, m2=m2, m3=m3, index=index, py=py)
if os.path.exists(htmlName):
os.remove(htmlName)
try:
html = open(htmlName, 'a', encoding='utf8')
html.write(htmlcode1)
html.write(tb)
html.write(ctt)
except:
html = open(htmlName, 'a', encoding='gbk')
html.write(htmlcode1)
html.write(tb)
html.write(ctt)
html.write('</body></html>')
html.close()
print("\n转换成功,保存在%s" % htmlName)
return
def txt2html_inonefile(txtName,
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'),
index=True,
py=False):
"""
txtName:文件的名称（含所在的文件夹）
index： True,将第四节的列入目录
False,不含第四节的目录
---------------
在txtName文件目录下生产一html文件。
"""
files = []
htmlcode1 = _hh(txtName)
if os.path.isfile(txtName):
path = os.path.abspath(txtName)
files.append(path)
htmlName = os.path.splitext(path)[0] + '.html'
else:
print("%s is not file...." % txtName)
sys.exit()
tb, ctt = make_Mulu_content(files, m1=m1, m2=m2, m3=m3, index=index, py=py)
if os.path.exists(htmlName):
os.remove(htmlName)
try:
html = open(htmlName, 'w', encoding='utf8')
html.write(htmlcode1)
html.write(tb)
html.write(ctt)
except:
html = open(htmlName, 'w', encoding='gbk')
html.write(htmlcode1)
html.write(tb)
html.write(ctt)
html.write('</body></html>')
html.close()
print("\n转换成功,保存在%s" % htmlName)
return
def C2html(txtpath,output='output',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,py=False):
"""
txtpath:为单独的文件、一系列文件或一段字符
并将这些文件中的内容输出到一份html 文件中
"""
p=getcsspath()
ft='''\n<link rel="stylesheet" type="text/css" href="%s" />'''
ll=title+'\n'+title1+ft%p+title2+'\n'
#print(ll)
files=[]
if isinstance(txtpath,list):
for f in txtpath:
if os.path.isfile(f) and (os.path.splitext(f)[1].lower() in ['.txt','.doc','.docx']):
files.append(f)
elif os.path.isfile(txtpath):
if os.path.splitext(txtpath)[1].lower() in ['.txt','.doc','.docx']:
files.append(txtpath)
elif isinstance(txtpath,str):
path123='tempsdfsf.txt'
fff=open(path123,'w',encoding='utf8')
fff.write(txtpath)
fff.close()
files.append(path123)
else:
sys.exit()
if output=='':
output='output.html'
else:
output=output+'.html'
if os.path.exists(output):
os.remove(output)
tb,ctt=make_Mulu_content(files,m1=m1,m2=m2,m3=m3,index=index,py=py)
try:
html=open(output,'a',encoding='utf8')
html.write(ll)
#html.write('<div id="content">\n')
html.write('<div id="content",style="background-color:#C7EDF0">\n')
html.write(tb)
html.write(ctt)
except:
html=open(output,'a',encoding='gbk')
html.write(ll)
#html.write('<div id="content">\n')
html.write('<div id="content",style="background-color:#C7EDF0">\n')
html.write(tb)
html.write(ctt)
html.write(endd)
html.close()
print("\n转换成功,保存在%s"%output)
try:
if os.path.exists(path123):
os.remove(path123)
except:
pass
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