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_txt(self, txt_id, threadnum):
intro = ''
ids = str(txt_id)
self.percent = 0
self.index = []
self.titleindex = []
self.Summary = []
self.fillNum = 0
self.rollSign = []
self.rollSignPlace = []
self.state = ''
self.href_list = []
self.td = []
self.failInfo = []
self.path = ''
self.textEdit.clear()
section_ct = 9999
# 获取文章网址
req_url = ids
nid = ids.split('=')[1]
apireq = 'https://app.jjwxc.net/androidapi/novelbasicinfo?novelId=' + nid
apivol = 'https://app.jjwxc.net/androidapi/chapterList?novelId=' + nid + '&more=0&whole=1'
# 通过cookie获取文章信息
res = requests.get(req_url, headers=self.headerss)
apires = requests.get(apireq, headers=self.headerss)
apicont = json.loads(apires.text)
if "message" in apicont and not "novelIntro" in apicont:
v = apicont["message"]
QMessageBox.warning(self, '警告', apicont["message"],
QMessageBox.Yes)
apicont = {
"message": v,
"novelId": "",
"novelName": "",
"authorId": "",
"authorName": "",
"novelClass": "",
"novelTags": "",
"novelTagsId": "",
"novelCover": "",
"originalCover": "",
"novelStep": "",
"novelIntro": "",
"novelIntroShort": "",
"isVip": "",
"isPackage": "",
"novelSize": "",
"novelsizeformat": "",
"novelChapterCount": "",
"renewDate": "",
"renewChapterId": "",
"renewChapterName": "",
"novelScore": "",
"islock": "",
"novelbefavoritedcount": "",
"novelbefavoritedcountformat": "",
"type_id": "",
"age": "",
"maxChapterId": "",
"chapterdateNewest": "",
"local": "",
"localImg": "",
"novelStyle": "",
"series": "",
"protagonist": "",
"costar": "",
"other": "",
"comment_count": "",
"nutrition_novel": "",
"ranking": "",
"novip_clicks": "",
"vipChapterid": "",
"isSign": "",
"ILTC": "",
"mainview": "",
"codeUrl": "",
"novelReviewScore": "",
"authorsayrule": "",
"copystatus": "",
"yellowcard": []
}
else:
# 获取目录
rc = requests.get(apivol, headers=self.headerss)
cdic = json.loads(rc.text)
cdic = cdic["chapterlist"]
# 对文案进行编码
ress = etree.HTML(
res.content.decode("GB18030",
"ignore").encode("utf-8",
"ignore").decode('utf-8'))
res.close()
# 获取文案
if self.special.isChecked():
intro = ress.xpath(
"//html/body/table/tr/td[1]/div[2]/div[@id='novelintro']")
else:
intro = apicont["novelIntro"]
intro = re.sub("<br/>", "\n", intro).splitlines()
# 获取标签
info = []
info.append("<b>标签：</b>" + apicont["novelTags"])
info.append(apicont["protagonist"])
info.append(apicont["costar"])
info.append(apicont["other"])
info.append("<b>简介：</b>" + apicont["novelIntroShort"])
infox = []
infox.append("文章类型：" + apicont["novelClass"])
infox.append("作品视角：" + apicont["mainview"])
infox.append("作品风格：" + apicont["novelStyle"])
infox.append("所属系列：" + apicont["series"])
if apicont["novelClass"] == "1":
infox.append("文章进度：连载")
elif apicont["novelClass"] == "2":
infox.append("文章进度：完结")
elif apicont["novelClass"] == "0":
infox.append("文章进度：暂停")
infox.append("全文字数：" + apicont["novelSize"] + "字")
# 获取封面
cover = apicont["novelCover"]
if cover != '':
try:
pres = requests.get(cover)
except Exception:
img = "0"
self.textEdit.append("【封面下载失败！请检查网络或尝试科学上网。】\n")
self.textEdit.moveCursor(self.textEdit.textCursor().End)
else:
img = pres.content
else:
img = "0"
fpi = re.findall(r'static.jjwxc.net/novelimage.php.novelid', cover)
if fpi:
img = '0'
# 获取标题和作者
xtitle = apicont["novelName"]
xaut = apicont["authorName"]
ti = xtitle + '-' + xaut
if self.state == 's':
ti = OpenCC('t2s').convert(ti)
elif self.state == 't':
ti = OpenCC('s2t').convert(ti)
self.textEdit.append("网址：" + ids + "\n小说信息：" + str(ti) + "\n")
self.textEdit.moveCursor(self.textEdit.textCursor().End)
self.setWindowTitle("正在下载：" + xtitle + '-' + xaut)
# 获取所有章节网址、标题、内容提要、卷标
loc = []
vcount = 0
for i in cdic:
if i["chaptertype"] == "1":
vcount += 1
v = i["chaptername"]
v = re.sub('&', '&', v)
v = re.sub('<', '<', v)
v = re.sub('>', '>', v)
if self.format.currentText() == "txt":
v = re.sub('</?\w+[^>]*>', '', v).strip()
v = "§ " + v + " §"
if self.selfvol.isChecked():
v = re.sub('\$1', str(vcount), self.voledit.text())
v = re.sub('\$2', i["chaptername"], v)
self.rollSign.append(v)
self.rollSignPlace.append(i["chapterid"])
else:
u = "https://app.jjwxc.net/androidapi/chapterContent?novelId=" + nid + "&chapterId=" + i[
"chapterid"]
self.href_list.append(u)
v = i["chaptername"]
v = re.sub('&', '&', v)
v = re.sub('&&#', '&#', v)
v = re.sub('</?\w+[^>]*>', '', v)
if self.format.currentText() == "txt":
v = re.sub('</?\w+[^>]*>', '', v)
self.titleindex.append(v.strip())
v = i["chapterintro"]
v = re.sub('&', '&', v)
v = re.sub('&&#', '&#', v)
if self.format.currentText() == "txt":
v = re.sub('</?\w+[^>]*>', '', v)
self.Summary.append(v.strip())
if i["islock"] != "0":
loc.append(i["chapterid"])
section_ct = len(self.href_list)
lockinfo = ''
self.textEdit.append("可下载章节数：" + str(section_ct) + "\n")
self.textEdit.moveCursor(self.textEdit.textCursor().End)
if loc != []:
i = ""
for x in loc:
i = i + x + " "
self.textEdit.append("被锁章节：" + i + "\n")
self.textEdit.moveCursor(self.textEdit.textCursor().End)
if self.format.currentText() == "txt":
lockinfo = "被锁章节：" + i + "\n"
else:
lockinfo = "<p><em>被锁章节：" + i + "</em></p>"
if self.state == 's':
lockinfo = OpenCC('t2s').convert(lockinfo)
elif self.state == 't':
lockinfo = OpenCC('s2t').convert(lockinfo)
# fillNum：填充序号的长度，例如：若全文有1437章，则每章序号有四位，依次为0001、0002……
self.fillNum = len(str(len(self.href_list)))
# 对标题进行操作，删除违规字符等
ti = re.sub('[\/:*?"<>|]', '_', ti)
ti = re.sub('&', '&', ti)
xauthref = "http://www.jjwxc.net/oneauthor.php?authorid=" + apicont[
"authorId"]
# 若文件名不想加编号，可以将这行删除
ti = ti + '.' + ids.split('=')[1]
ti = re.sub('\r', '', ti)
v = ""
# 打开小说文件写入小说相关信息
path = os.getcwd()
self.path = path
if os.path.exists(ti):
os.chdir(ti)
else:
os.mkdir(ti)
os.chdir(ti)
ppp = os.getcwd()
for vol in range(len(self.rollSignPlace)):
self.rollSignPlace[vol] = self.rollSignPlace[vol].strip()
volt = self.rollSignPlace[vol]
ros = self.rollSign[vol]
nm = 'z' + str(int(volt) - 1).zfill(4) + '_vol.xhtml'
if self.state == 's':
ros = OpenCC('t2s').convert(ros)
elif self.state == 't':
rose = OpenCC('s2t').convert(ros)
with open(nm, 'w', encoding='utf-8') as f:
f.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>''' + ros + '''</title><meta charset="utf-8"/>
<link href="sgc-nav.css" rel="stylesheet" type="text/css"/></head>
<body><h1>''' + ros + '''</h1></body></html>'''))
self.index = []
# 保存封面图片
if img != "0" and self.cover.isChecked(
) and not self.format.currentText() == "txt":
with open("p.jpg", 'wb') as pic:
pic.write(img)
# 写入封面
with open("C.xhtml", 'w', encoding='utf-8') as f:
f.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>Cover</title></head>
<body><div style="text-align: center; padding: 0pt; margin: 0pt;">
<svg xmlns="http://www.w3.org/2000/svg" height="100%" preserveAspectRatio="xMidYMid meet" version="1.1" width="100%" xmlns:xlink="http://www.w3.org/1999/xlink">
<image width="100%" xlink:href="p.jpg"/></svg></div></body></html>''')
# 写入文章信息页
if self.format.currentText() == "txt":
TOC = xtitle + '\n'
TOC += '作者：' + xaut + "\n"
TOC += '源网址：' + req_url + '\n'
else:
TOC = "<h1 class='title' title='" + xtitle + "-" + xaut + "'><a href='" + req_url + "'>" + xtitle + "</a></h1>"
TOC += "<h2 class='sigil_not_in_toc title'>作者：<a href='" + xauthref + "'>" + xaut + "</a></h2>"
TOC += '''<blockquote>'''
# 生成目录文字
for l in self.href_list:
title = ''
titleOrigin = l.split('=')
if titleOrigin[2] in loc:
title += "[锁]"
i = self.href_list.index(l)
#
title += str(titleOrigin[2]).zfill(self.fillNum) + " "
#
title = title + self.titleindex[i].strip() + " "
#
title = title + self.Summary[i].strip()
if self.state == 's':
title = OpenCC('t2s').convert(title)
elif self.state == 't':
title = OpenCC('s2t').convert(title)
self.index.append(title)
for ix in infox:
ix = ix.strip()
ix = re.sub('\n', '', ix)
ix = re.sub(' +', '', ix)
if self.format.currentText() == "txt":
TOC += ix + "\n"
else:
TOC += "<p>" + ix + "</p>"
if self.format.currentText() == "txt":
TOC += "文案：\n"
else:
TOC += "</blockquote>"
TOC += "<hr/><p><b>文案：</b></p>"
if self.special.isChecked():
v = etree.tostring(intro[0], encoding="utf-8").decode()
TOC += v
else:
for nx in intro:
v = re.sub(' +', ' ', str(nx)).strip()
v = re.sub('>', '>', v)
v = re.sub('<', '<', v)
if v != "" and self.format.currentText() == "txt":
TOC += v + "\n"
elif v:
TOC += "<p>" + v + "</p>"
if "立意:" in TOC:
TOC = re.sub('<p>立意:', '<hr/><p><b>立意</b>：', TOC)
else:
TOC += '<hr/>'
if self.format.currentText() == "txt":
for v in info:
TOC += re.sub("<.*?>", "", v) + '\n'
if self.state == 's':
TOC = OpenCC('t2s').convert(TOC)
elif self.state == 't':
TOC = OpenCC('s2t').convert(TOC)
with open("info.txt", 'w', encoding='utf-8') as fo:
fo.write(TOC.strip() + '\n')
fo.write(lockinfo.strip() + '\n')
else:
for v in info:
v = re.sub("主角：", "<b>主角：</b>", v)
v = re.sub("配角：", "<b>配角：</b>", v)
v = re.sub("其它：", "<b>其它：</b>", v)
TOC += "<p>" + v + "</p>"
if self.state == 's':
TOC = OpenCC('t2s').convert(TOC)
elif self.state == 't':
TOC = OpenCC('s2t').convert(TOC)
with open("info.xhtml", 'w', encoding='utf-8') as fo:
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><meta charset="utf-8"/>
<link href="sgc-nav.css" rel="stylesheet" type="text/css"/></head>
<body>''' + TOC + lockinfo + '''</body></html>''')
tlist = []
# 获取每一章内容
with concurrent.futures.ThreadPoolExecutor(
max_workers=threadnum) as executor:
tlist = {
executor.submit(self.get_sin, i): i
for i in self.href_list
}
for future in concurrent.futures.as_completed(tlist):
if self.percent < section_ct:
self.progressBar.setValue(
int(100 * self.percent / section_ct))
self.progressBar.update()
self.pct.setText(
str(self.percent) + '/' + str(section_ct))
self.setWindowTitle("正在下载：" + xtitle + '-' + xaut +
" (" + self.pct.text() + ")")
QApplication.processEvents()
if self.percent < section_ct:
QMessageBox.warning(
self, '警告', '请检查cookie是否正确！\n章节：' + self.currentTitle,
QMessageBox.Yes)
self.progressBar.setValue(int(100 * self.percent / section_ct))
self.progressBar.update()
self.textEdit.append('\n 下载完成，总进度：' + str(self.percent) + '/' +
str(section_ct))
self.textEdit.moveCursor(self.textEdit.textCursor().End)
time.sleep(0.1)
self.pct.setText(str(self.percent) + '/' + str(section_ct))
'''
for i in self.href_list:
self.get_sin(i)
'''
if self.failInfo:
self.failInfo.sort()
vs = ""
for ss in self.failInfo:
vs = vs + ss + "|"
self.textEdit.append("\n未购买或加载失败章节：")
self.textEdit.append(vs[:-1] + "\n")
self.textEdit.moveCursor(self.textEdit.textCursor().End)
if self.format.currentText() == "txt":
# txt整合
os.chdir(path)
f = open(ti + ".txt", 'w', encoding='utf-8')
filenames = os.listdir(ppp)
i = 0
for filename in filenames:
filepath = ppp + '\\' + filename
for line in open(filepath,
encoding='utf-8',
errors='ignore'):
f.writelines(line)
f.close()
shutil.rmtree(ppp)
self.textEdit.append("\ntxt文件整合完成")
self.textEdit.moveCursor(self.textEdit.textCursor().End)
else:
# 保存为epub
os.chdir(path)
epub_name = ti + ".epub"
epub = zipfile.ZipFile(epub_name, 'w')
if self.format.currentText() == "epub2":
epubfile = EPUB2.epubfile()
if self.hvol.isChecked():
epubfile.htmlvol = 1
else:
epubfile = EPUB3.epubfile()
epubfile.csstext = self.cssedit.toPlainText()
epubfile.createEpub(epub, xaut, xtitle, ti, self.index,
self.rollSign, path)
self.textEdit.append("\nepub打包完成")
self.textEdit.moveCursor(self.textEdit.textCursor().End)
self.setWindowTitle("下载完成：" + xtitle + '-' + xaut + " (" +
self.pct.text() + ")")
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
