def get_sin(self, l):
titleOrigin = l.split('=')
i = self.href_list.index(l)
#dot=etree.HTML(cont.content)
fontfamily = ''
cvlist = []
cvdic = []
cont = ''
dot = ''
codetext = ''
badgateway = True
while (badgateway):
cont = requests.get(l, headers=self.headerss)
dot = etree.HTML(
cont.content.decode('gb18030',
"ignore").encode("utf-8").decode('utf-8'))
codetext = etree.tostring(dot, encoding="utf-8").decode()
bdw = re.findall('<h1>502 Bad Gateway</h1>', codetext)
if bdw == []:
badgateway = False
else:
time.sleep(1)
#字体反爬虫
fontsrc = re.findall(
r'//static.jjwxc.net/tmp/fonts/.*?woff2.h=my.jjwxc.net', codetext)
if fontsrc != []:
fontsrc = "http:" + fontsrc[0]
fontname = re.sub('http://static.jjwxc.net/tmp/fonts/', '',
fontsrc)
fontname = re.sub('.h=my.jjwxc.net', '', fontname)
fontfamily = re.sub('.woff2', '', fontname)
cvdic = []
if not os.path.exists(self.path + "/Fonts/" + fontfamily + '.txt'):
#解析json文件
r = requests.get('http://jjwxc.yooooo.us/' + fontfamily +
'.json')
fonttxt = re.sub('{"status": 0, "data": ', '', r.text)
fonttxt = re.sub('}}', '}', fonttxt)
cdic = json.loads(fonttxt)
fonttxt = ''
f = open(self.path + "/Fonts/" + fontfamily + ".txt",
"w",
encoding='utf-8')
for s, v in cdic.items():
fonttxt = fonttxt + '&#x' + s + ';-' + v + '\n'
fonttxt.strip()
f.write(fonttxt)
f.close()
'''
#若需要下载ttf文件，可运行下方代码
fontwb=requests.get(re.sub('woff2','ttf',fontsrc)).content
fontf=open(self.path+"/Fonts/"+fontfamily+'.ttf','wb')
fontf.write(fontwb)
fontf.close()
'''
try:
with open(self.path + "/Fonts/" + fontfamily + ".txt",
"r",
encoding='utf-8') as f:
cvlist = f.readlines()
for y in range(len(cvlist)):
cvdic.append(cvlist[y].split('-'))
cvdic = dict(cvdic)
except:
t = 1
if cvlist != []:
fontfamily += '_c'
elif fontfamily not in self.fontlist:
self.fontlist.append(fontfamily)
#tex:正文
tex = dot.xpath('//*[@id="oneboolt"]/tr[2]/td[1]/div/text()')
#tex1:作话
tex1 = dot.xpath("//div[@class='readsmall']/text()")
#sign:作话位置
sign = dot.xpath("//*[@id='oneboolt']/tr[2]/td[1]/div/div[4]/@class")
title = ''
#序号填充
if self.titleInfo[0] == '1':
title = str(titleOrigin[2]).zfill(self.fillNum) + "#"
#章节名称
if self.titleInfo[1] == '1':
title = title + " " + self.titleindex[i].strip()
#内容提要
if self.titleInfo[2] == '1':
title = title + " " + self.Summary[i].strip()
title = re.sub('&', '&', title)
title = re.sub('<', '<', title)
title = re.sub('>', '>', title)
if self.state == 's':
title = OpenCC('t2s').convert(title)
elif self.state == 't':
title = OpenCC('s2t').convert(title)
if self.href_list[i] in self.rollSignPlace:
v = self.rollSign[self.rollSignPlace.index(l)]
if self.state == 's':
v = OpenCC('t2s').convert(
self.rollSign[self.rollSignPlace.index(l)])
elif self.state == 't':
v = OpenCC('s2t').convert(
self.rollSign[self.rollSignPlace.index(l)])
#创建章节文件
fo = open("z" + str(titleOrigin[2].zfill(4)) + ".txt",
'w',
encoding='utf-8')
#写入卷标
if self.href_list[i] in self.rollSignPlace:
v = re.sub('&', '&', v)
v = re.sub('<', '<', v)
v = re.sub('>', '>', v)
fo.write("\r\n\r\n" + v.rstrip() + '\r\n')
print("\r\n" + v + "\r\n")
fo.write(title + '\r\n')
#写入标题
else:
fo.write("\r\n\r\n" + title + "\r\n")
if len(tex) == 0:
self.failInfo.append(titleOrigin[2].zfill(self.fillNum))
fo.write('下载失败！')
else:
#反爬虫处理，必须把对照表TXT文件下载至Fonts文件夹
if cvdic != []:
for y in range(len(tex)):
for s, v in cvdic.items():
if not s == 'x"/;':
s = re.sub(r'&#x', r'\\u', s)
s = re.sub(
';', '',
s).encode('utf-8').decode('unicode_escape')
tex[y] = re.sub(s, v.strip(), tex[y])
cvdic = cvlist = []
#作话在文前的情况
if str(sign) == "['readsmall']":
for m in tex1: #删除无用文字及多余空格空行
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('<', '<', v)
v = re.sub('>', '>', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '作者有话要说：\n', v)
if v != "": #按行写入正文
fo.write(v + "\n")
if len(tex1) != 0:
fo.write("\n*\r\n")
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('<', '<', v)
v = re.sub('>', '>', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write(v + "\n")
else: #作话在文后的情况
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('<', '<', v)
v = re.sub('>', '>', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write(v + "\n")
if len(tex1) != 0:
fo.write("\n*\r\n")
for m in tex1:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('<', '<', v)
v = re.sub('>', '>', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '作者有话要说：\n', v)
if v != "":
fo.write(v + "\n")
fo.close()
self.percent += 1
def get_sin(self, l):
titleOrigin = l.split('=')
i = self.href_list.index(l)
cont = requests.get(l, headers=self.headerss).content
dot = etree.HTML(
cont.decode("GB18030", "ignore").encode("utf-8",
"ignore").decode('utf-8'))
#tex:正文
tex = dot.xpath(
"//html/body/table[@id='oneboolt']/tr[2]/td[1]/div[@class='noveltext']/text()"
)
#he:标题
he = dot.xpath(
"//html/body/table[@id='oneboolt']/tr[2]/td[1]/div[@class='noveltext']/div[2]/h2/text()"
)
#tex1:作话
tex1 = dot.xpath(
"//html/body/table[@id='oneboolt']/tr[2]/td[1]/div[@class='noveltext']/div[@class='readsmall']/text()"
)
#sign:作话位置
sign = dot.xpath("//*[@id='oneboolt']/tr[2]/td[1]/div/div[4]/@class")
title = ''
#序号填充
if self.titleInfo[0] == '1':
title = str(titleOrigin[2]).zfill(self.fillNum)
#章节名称
if self.titleInfo[1] == '1':
title = title + " " + self.titleindex[i].strip()
#内容提要
if self.titleInfo[2] == '1':
title = title + " " + self.Summary[i].strip()
if self.state == 's':
title = OpenCC('t2s').convert(title)
elif self.state == 't':
title = OpenCC('s2t').convert(title)
if self.href_list[i] in self.rollSignPlace:
v = self.rollSign[self.rollSignPlace.index(l)]
if self.state == 's':
v = OpenCC('t2s').convert(
self.rollSign[self.rollSignPlace.index(l)])
elif self.state == 't':
v = OpenCC('s2t').convert(
self.rollSign[self.rollSignPlace.index(l)])
#创建章节文件
fo = open("z" + str(titleOrigin[2].zfill(4)) + ".xhtml",
'w',
encoding='utf-8')
fo.write('''<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
<head><title>''' + title + '''</title>
<meta charset="utf-8"/>
<link href="sgc-nav.css" rel="stylesheet" type="text/css"/>
</head><body>''')
#写入卷标
if self.href_list[i] in self.rollSignPlace:
fo.write("<h1>" + v.rstrip() + "</h1>")
print("\r\n" + v + "\r\n")
fo.write("<h2 id='v'><a href='" + l + "'>" + title + "</a></h2>")
#写入标题
else:
fo.write('<h2><a href="' + l + '">' + title + "</a></h2>")
if len(he) == 0:
self.failInfo.append(titleOrigin[2].zfill(self.fillNum))
#print("第"+titleOrigin[2]+"章未购买或加载失败")
else:
#作话在文前的情况
if str(sign) == "['readsmall']":
fo.write('''<blockquote>''')
for m in tex1: #删除无用文字及多余空格空行
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' +', ' ', vv).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '<b>作者有话要说</b>：</p><p>', v)
if v != "": #按行写入正文
fo.write("<p>" + v + "</p>")
fo.write("</blockquote>")
if len(tex1) != 0:
fo.write("<hr/>")
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' +', ' ', vv).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
v = re.sub(' ', '', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write("<p>" + v + "</p>")
else: #作话在文后的情况
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' +', ' ', vv).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
v = re.sub(' ', '', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write("<p>" + v + "</p>")
if len(tex1) != 0:
fo.write("<hr/>")
fo.write('''<blockquote>''')
for m in tex1:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' +', ' ', vv).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '<b>作者有话要说</b>：</p><p>', v)
if v != "":
fo.write("<p>" + v + "</p>")
if len(tex1) != 0:
fo.write("</blockquote>")
fo.write("</body></html>")
fo.close()
self.percent += 1
def get_sin(self, l):
titleOrigin = l.split('=')
i = self.href_list.index(l)
#dot=etree.HTML(cont.content)
fontfamily = ''
cvlist = []
cvdic = []
cont = ''
dot = ''
codetext = ''
badgateway = True
while (badgateway):
cont = requests.get(l, headers=self.headerss)
dot = etree.HTML(
cont.content.decode('gb18030',
"ignore").encode("utf-8").decode('utf-8'))
codetext = etree.tostring(dot, encoding="utf-8").decode()
bdw = re.findall('<h1>502 Bad Gateway</h1>', codetext)
if bdw == []:
badgateway = False
else:
time.sleep(1)
#字体反爬虫
fontsrc = re.findall(
r'//static.jjwxc.net/tmp/fonts/.*?woff2.h=my.jjwxc.net', codetext)
if fontsrc != []:
fontsrc = "http:" + fontsrc[0]
fontname = re.sub('http://static.jjwxc.net/tmp/fonts/', '',
fontsrc)
fontname = re.sub('.h=my.jjwxc.net', '', fontname)
fontfamily = re.sub('.woff2', '', fontname)
cvdic = []
if not os.path.exists(self.path + "/Fonts/" + fontfamily + '.txt'):
#解析json文件
r = requests.get('http://jjwxc.yooooo.us/' + fontfamily +
'.json')
fonttxt = re.sub('{"status": 0, "data": ', '', r.text)
fonttxt = re.sub('}}', '}', fonttxt)
cdic = json.loads(fonttxt)
fonttxt = ''
f = open(self.path + "/Fonts/" + fontfamily + ".txt",
"w",
encoding='utf-8')
for s, v in cdic.items():
fonttxt = fonttxt + '&#x' + s + ';-' + v + '\n'
fonttxt.strip()
f.write(fonttxt)
f.close()
'''
#若需要下载ttf文件，可运行下方代码
fontwb=requests.get(re.sub('woff2','ttf',fontsrc)).content
fontf=open(self.path+"/Fonts/"+fontfamily+'.ttf','wb')
fontf.write(fontwb)
fontf.close()
'''
try:
with open(self.path + "/Fonts/" + fontfamily + ".txt",
"r",
encoding='utf-8') as f:
cvlist = f.readlines()
for y in range(len(cvlist)):
cvdic.append(cvlist[y].split('-'))
cvdic = dict(cvdic)
except:
t = 1
if cvlist != []:
fontfamily += '_c'
elif fontfamily not in self.fontlist:
self.fontlist.append(fontfamily)
self.fontcss += '''@font-face{font-family: "%s";
src:url("%s") format('woff2'),
url("../font/%s") format('woff2'),
url("../font/%s.ttf") format("truetype");}
.%s{font-family:"%s",serif;}
''' % (fontfamily, fontsrc, fontname, fontfamily, fontfamily, fontfamily)
#tex:正文
tex = dot.xpath('//*[@id="oneboolt"]/tr[2]/td[1]/div/text()')
#tex1:作话
tex1 = dot.xpath("//div[@class='readsmall']/text()")
#sign:作话位置
sign = dot.xpath("//*[@id='oneboolt']/tr[2]/td[1]/div/div[4]/@class")
title = ''
#序号填充
if self.titleInfo[0] == '1':
title = str(titleOrigin[2]).zfill(self.fillNum)
#章节名称
if self.titleInfo[1] == '1':
title = title + " " + self.titleindex[i].strip()
#内容提要
if self.titleInfo[2] == '1':
title = title + " " + self.Summary[i].strip()
title = title.strip()
if self.state == 's':
title = OpenCC('t2s').convert(title)
elif self.state == 't':
title = OpenCC('s2t').convert(title)
if self.href_list[i] in self.rollSignPlace:
v = self.rollSign[self.rollSignPlace.index(l)]
if self.state == 's':
v = OpenCC('t2s').convert(
self.rollSign[self.rollSignPlace.index(l)])
elif self.state == 't':
v = OpenCC('s2t').convert(
self.rollSign[self.rollSignPlace.index(l)])
#创建章节文件
fo = open("z" + str(titleOrigin[2].zfill(4)) + ".xhtml",
'w',
encoding='utf-8')
fo.write('''<?xml version="1.0" encoding="UTF-8" standalone="no" ?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<title>''' + title + '''</title>
<meta charset="utf-8"/>
<link href="sgc-nav.css" rel="stylesheet" type="text/css"/>
</head><body class="''' + fontfamily + '''">''')
#写入卷标
if self.href_list[i] in self.rollSignPlace:
fo.write("<h1>" + v.rstrip() + "</h1>")
print("\r\n" + v + "\r\n")
fo.write("<h2 id='v'>" + title + "</h2>")
#写入标题
else:
fo.write('<h2>' + title + "</h2>")
if len(tex) == 0:
self.failInfo.append(titleOrigin[2].zfill(self.fillNum))
#print("第"+titleOrigin[2]+"章未购买或加载失败")
else:
#反爬虫处理，必须把对照表TXT文件下载至Fonts文件夹
if cvdic != []:
for y in range(len(tex)):
for s, v in cvdic.items():
if not s == 'x"/;':
s = re.sub(r'&#x', r'\\u', s)
s = re.sub(
';', '',
s).encode('utf-8').decode('unicode_escape')
tex[y] = re.sub(s, v.strip(), tex[y])
cvdic = cvlist = []
#作话在文前的情况
if str(sign) == "['readsmall']":
fo.write('''<blockquote>''')
for m in tex1: #删除无用文字及多余空格空行
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '<b>作者有话要说</b>：</p><p>', v)
if v != "": #按行写入正文
fo.write("<p>" + v + "</p>")
fo.write("</blockquote>")
if len(tex1) != 0:
fo.write("<hr/>")
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write("<p>" + v + "</p>")
else: #作话在文后的情况
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write("<p>" + v + "</p>")
if len(tex1) != 0:
fo.write("<hr/>")
fo.write('''<blockquote>''')
for m in tex1:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' ', '', vv)
v = re.sub(' +', ' ', v).strip()
v = re.sub('&', '&', v)
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '<b>作者有话要说</b>：</p><p>', v)
if v != "":
fo.write("<p>" + v + "</p>")
if len(tex1) != 0:
fo.write("</blockquote>")
fo.write("</body></html>")
fo.close()
self.percent += 1
def get_sin(self, l):
titleOrigin = l.split('=')
i = self.href_list.index(l)
cont = requests.get(l, headers=self.headerss).content
dot = etree.HTML(
cont.decode("GB18030", "ignore").encode("utf-8",
"ignore").decode('utf-8'))
fontfamily = ''
cvlist = []
cvdic = []
#字体反爬虫
codetext = etree.tostring(dot, encoding="utf-8").decode()
fontsrc = re.findall(
r'//static.jjwxc.net/tmp/fonts/.*?woff2.h=my.jjwxc.net', codetext)
if fontsrc != []:
fontsrc = "http:" + fontsrc[0]
fontname = re.sub('http://static.jjwxc.net/tmp/fonts/', '',
fontsrc)
fontname = re.sub('.h=my.jjwxc.net', '', fontname)
fontfamily = re.sub('.woff2', '', fontname)
try:
with open(self.path + "/Fonts/" + fontfamily + ".txt",
"r",
encoding='utf-8') as f:
cvlist = f.readlines()
for y in range(len(cvlist)):
cvdic.append(cvlist[y].split('-'))
cvdic = dict(cvdic)
except:
y = 1
if not os.path.exists(self.path + "/Fonts/" + fontname):
fontwb = requests.get(fontsrc).content
fontf = open(self.path + "/Fonts/" + fontname, 'wb')
fontf.write(fontwb)
fontf.close()
if cvlist != []:
fontfamily = ''
elif fontfamily not in self.fontlist:
self.fontlist.append(fontfamily)
#tex:正文
tex = dot.xpath('//*[@id="oneboolt"]/tr[2]/td[1]/div/text()')
#tex1:作话
tex1 = dot.xpath("//div[@class='readsmall']/text()")
#sign:作话位置
sign = dot.xpath("//*[@id='oneboolt']/tr[2]/td[1]/div/div[4]/@class")
title = ''
#序号填充
if self.titleInfo[0] == '1':
title = str(titleOrigin[2]).zfill(self.fillNum) + "#"
#章节名称
if self.titleInfo[1] == '1':
title = title + " " + self.titleindex[i].strip()
#内容提要
if self.titleInfo[2] == '1':
title = title + " " + self.Summary[i].strip()
if self.state == 's':
title = OpenCC('t2s').convert(title)
elif self.state == 't':
title = OpenCC('s2t').convert(title)
if self.href_list[i] in self.rollSignPlace:
v = self.rollSign[self.rollSignPlace.index(l)]
if self.state == 's':
v = OpenCC('t2s').convert(
self.rollSign[self.rollSignPlace.index(l)])
elif self.state == 't':
v = OpenCC('s2t').convert(
self.rollSign[self.rollSignPlace.index(l)])
#创建章节文件
fo = open("z" + str(titleOrigin[2].zfill(4)) + ".txt",
'w',
encoding='utf-8')
#写入卷标
if self.href_list[i] in self.rollSignPlace:
fo.write("\r\n\r\n" + v.rstrip() + '\r\n')
print("\r\n" + v + "\r\n")
fo.write(title + '\r\n')
#写入标题
else:
fo.write("\r\n\r\n" + title + "\r\n")
if len(tex) == 0:
self.failInfo.append(titleOrigin[2].zfill(self.fillNum))
fo.write('下载失败！')
else:
#反爬虫处理，必须把对照表TXT文件下载至Fonts文件夹
if cvdic != []:
for y in range(len(tex)):
for s, v in cvdic.items():
s = re.sub(r'&#x', r'\\u', s)
s = re.sub(r';', '',
s).encode('utf-8').decode('unicode_escape')
tex[y] = re.sub(s, v.strip(), tex[y])
cvdic = cvlist = 0
#作话在文前的情况
if str(sign) == "['readsmall']":
for m in tex1: #删除无用文字及多余空格空行
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' +', ' ', vv).strip()
v = re.sub(' ', '', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '作者有话要说：\n', v)
if v != "": #按行写入正文
fo.write(v + "\n")
if len(tex1) != 0:
fo.write("\n*\r\n")
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' +', ' ', vv).strip()
v = re.sub(' ', '', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write(v + "\n")
else: #作话在文后的情况
for tn in tex:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(tn))
v = re.sub(' +', ' ', vv).strip()
v = re.sub(' ', '', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
if v != "":
fo.write(v + "\n")
if len(tex1) != 0:
fo.write("\n*\r\n")
for m in tex1:
vv = re.sub('@无限好文，尽在晋江文学城', '', str(m))
v = re.sub(' +', ' ', vv).strip()
v = re.sub(' ', '', v)
if self.state == 's':
v = OpenCC('t2s').convert(v)
elif self.state == 't':
v = OpenCC('s2t').convert(v)
v = re.sub('作者有话要说：', '作者有话要说：\n', v)
if v != "":
fo.write(v + "\n")
fo.close()
self.percent += 1
