def _extract(self):
content = self._content
p1 = content.find('<div class="b-story-header">')
self._intro = ''
if p1 < 0:
return -2
p1 = content.find('<h1>', p1)
if p1 < 0:
return -2
p2 = content.find('</h1>', p1)
if p2 < 0:
return -2
title = content[p1 + 4:p2]
self._intro = shell.html2text(title).strip() + '\n\n\n'
p1 = content.find('<select name="page">')
if p1 >= 0:
p2 = content.find('</select>', p1)
if p2 < 0:
return -1
count = 0
self._index = []
while p1 < p2:
p1 = content.find('<option value="', p1)
if p1 < 0 or p1 >= p2:
break
p1 = p1 + 15
pp = content.find('"', p1)
if p1 < 0:
break
text = content[p1:pp].strip()
p1 = pp
self._index.append(text)
else:
self._index = ['1']
return 0
def chapter(self, n):
content = self.read_chapter(n)
p1 = content.find('<div class="b-story-body-x')
if p1 < 0:
print 'suck1'
return None
p1 = content.find('>', p1)
if p1 < 0:
print 'suck2'
return None
p2 = content.find('</div>', p1)
html = content[p1 + 1:p2]
return shell.html2text(html)
def __init__(self, url):
self._url = url
self._content = shell.request_safe(url).decode('gbk', 'ignore')
#self._content = open('content.txt', 'r').read().decode('gbk')
content = self._content
p = re.compile(r'<dd><a\shref="(\d*.html)" title="(.*)"')
result = [[0, x[0], x[1]] for x in p.findall(content)]
for m in result:
m[0] = int(re.findall('\d*', m[1])[0])
result.sort()
self._index = [(m[1], m[2]) for m in result]
p1 = content.find('<div class="mulu_bookinfo">')
p2 = content.find('</div>', p1)
intro = ''
if p1 >= 0 and p2 >= 0:
text = content[p1:p2]
intro = shell.html2text(text) + '\n\n'
self._intro = intro
def __init__(self, url):
self._url = url
if 1:
self._content = shell.request_safe(url).decode('utf-8', 'ignore')
self._content = self._content.encode('gbk', 'ignore')
self._content = self._content.decode('gbk', 'ignore')
else:
self._content = open('mangg.txt', 'r').read().decode('gbk')
content = self._content
p = re.compile(r'<dd><a href="([^\.]*).html">([^<]*)</a>')
result = [[0, x[0], x[1]] for x in p.findall(content)]
for m in result:
m[0] = int(re.findall('/id\d*/(\d*)', m[1])[0])
result.sort()
self._index = [(m[1] + '.html', m[2]) for m in result]
intro = ''
p1 = content.find('<div id="intro">')
p2 = content.find('</div>', p1)
if p1 >= 0 and p2 >= 0:
intro = content[p1:p2]
intro = shell.html2text(intro) + '\n\n'
self._intro = intro
def chapter(self, n):
content = self.read_chapter(n)
p = re.compile(r'<div id="content">(.*)</div>')
result = p.findall(content)
html = result[0]
return shell.html2text(html)