mirror of
https://github.com/wassname/FanFicFare.git
synced 2026-09-10 11:40:24 +08:00
Starting to use source control again after a long break :-)
This commit is contained in:
sigizmund
+524
-223
File diff suppressed because it is too large
Load Diff
+2
-1
@@ -36,7 +36,8 @@ CONTENT_START = '''<?xml version="1.0"?>
|
||||
<dc:title>%s</dc:title>
|
||||
<dc:creator opf:role="aut">%s</dc:creator>
|
||||
<dc:language>en-UK</dc:language>
|
||||
<dc:rights></dc:rights>
|
||||
<dc:rights></dc:rights>
|
||||
<dc:subject>fanfiction</dc:subject>
|
||||
<dc:publisher>sgzmd</dc:publisher>
|
||||
<dc:identifier id="BookId">urn:uuid:sigizmund.com062820072147132</dc:identifier>
|
||||
</metadata>
|
||||
|
||||
@@ -118,20 +118,39 @@ class FFNet(FanfictionSiteAdapter):
|
||||
textbuf = ''
|
||||
emit = False
|
||||
|
||||
for l in lines:
|
||||
if l.find('<!-- start story -->') != -1:
|
||||
#s2 = bs.BeautifulStoneSoup(l)
|
||||
#return s2.div.prettify()
|
||||
emit = True
|
||||
|
||||
if emit:
|
||||
textbuf = textbuf + "\n" + l
|
||||
|
||||
if l.find('<!-- end story -->') != -1:
|
||||
emit = False
|
||||
olddata = data
|
||||
try:
|
||||
data = data.decode('utf8')
|
||||
except:
|
||||
data = olddata
|
||||
|
||||
s2 = bs.BeautifulStoneSoup(textbuf)
|
||||
return s2.div.prettify()
|
||||
try:
|
||||
soup = bs.BeautifulStoneSoup(data)
|
||||
except:
|
||||
logging.info("Failed to decode: <%s>" % data)
|
||||
soup = None
|
||||
div = soup.find('div', {'id' : 'storytext'})
|
||||
if None == div:
|
||||
return '<html/>'
|
||||
|
||||
return div.prettify()
|
||||
|
||||
#
|
||||
# for l in lines:
|
||||
# if l.find("<div id=storytextp class=storytextp") != -1 or l.find('<!-- start story -->') != -1 or l.find('<div id="storytextp"') != -1:
|
||||
# logging.debug("starting at line: %s" % l)
|
||||
# #s2 = bs.BeautifulStoneSoup(l)
|
||||
# #return s2.div.prettify()
|
||||
# emit = True
|
||||
#
|
||||
# if emit:
|
||||
# textbuf = textbuf + "\n" + l
|
||||
#
|
||||
# if l.find("</div><div style='height:10px'></div> ") != -1 or l.find('<!-- end story -->') != -1:
|
||||
# emit = False
|
||||
#
|
||||
# s2 = bs.BeautifulStoneSoup(textbuf)
|
||||
# return s2.div.prettify()
|
||||
|
||||
|
||||
def setLogin(self, login):
|
||||
@@ -162,7 +181,7 @@ class FFA_UnitTests(unittest.TestCase):
|
||||
f = FFNet('http://www.fanfiction.net/s/5257563/1')
|
||||
urls = f.extractIndividualUrls()
|
||||
|
||||
self.assertEquals(8, len(urls))
|
||||
self.assertEquals(10, len(urls))
|
||||
|
||||
def testGetText(self):
|
||||
url = 'http://www.fanfiction.net/s/5257563/1'
|
||||
|
||||
@@ -17,10 +17,10 @@ class FicWad(FanfictionSiteAdapter):
|
||||
self.url = url
|
||||
self.host = up.urlparse(url).netloc
|
||||
|
||||
def requiresLogin(self, url):
|
||||
def requiresLogin(self, url = None):
|
||||
return False
|
||||
|
||||
def performLogin(self, url):
|
||||
def performLogin(self, url = None):
|
||||
pass
|
||||
|
||||
def setLogin(self, login):
|
||||
@@ -37,7 +37,7 @@ class FicWad(FanfictionSiteAdapter):
|
||||
self.storyName = title.split('::')[0].strip()
|
||||
|
||||
author = soup.find('span', {'class' : 'author'})
|
||||
self.authorName = author.a.string
|
||||
self.authorName = str(author.a.string)
|
||||
|
||||
print('Story "%s" by %s' % (self.storyName, self.authorName))
|
||||
|
||||
|
||||
+450
@@ -0,0 +1,450 @@
|
||||
#!/usr/bin/env python
|
||||
"""html2text: Turn HTML into equivalent Markdown-structured text."""
|
||||
__version__ = "2.37"
|
||||
__author__ = "Aaron Swartz (me@aaronsw.com)"
|
||||
__copyright__ = "(C) 2004-2008 Aaron Swartz. GNU GPL 3."
|
||||
__contributors__ = ["Martin 'Joey' Schulze", "Ricardo Reyes", "Kevin Jay North"]
|
||||
|
||||
# TODO:
|
||||
# Support decoded entities with unifiable.
|
||||
|
||||
if not hasattr(__builtins__, 'True'): True, False = 1, 0
|
||||
import re, sys, urllib, htmlentitydefs, codecs, StringIO, types
|
||||
import sgmllib
|
||||
import urlparse
|
||||
sgmllib.charref = re.compile('&#([xX]?[0-9a-fA-F]+)[^0-9a-fA-F]')
|
||||
|
||||
try: from textwrap import wrap
|
||||
except: pass
|
||||
|
||||
# Use Unicode characters instead of their ascii psuedo-replacements
|
||||
UNICODE_SNOB = 0
|
||||
|
||||
# Put the links after each paragraph instead of at the end.
|
||||
LINKS_EACH_PARAGRAPH = 0
|
||||
|
||||
# Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.)
|
||||
BODY_WIDTH = 78
|
||||
|
||||
# Don't show internal links (href="#local-anchor") -- corresponding link targets
|
||||
# won't be visible in the plain text file anyway.
|
||||
SKIP_INTERNAL_LINKS = False
|
||||
|
||||
### Entity Nonsense ###
|
||||
|
||||
def name2cp(k):
|
||||
if k == 'apos': return ord("'")
|
||||
if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3
|
||||
return htmlentitydefs.name2codepoint[k]
|
||||
else:
|
||||
k = htmlentitydefs.entitydefs[k]
|
||||
if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1
|
||||
return ord(codecs.latin_1_decode(k)[0])
|
||||
|
||||
unifiable = {'rsquo':"'", 'lsquo':"'", 'rdquo':'"', 'ldquo':'"',
|
||||
'copy':'(C)', 'mdash':'--', 'nbsp':' ', 'rarr':'->', 'larr':'<-', 'middot':'*',
|
||||
'ndash':'-', 'oelig':'oe', 'aelig':'ae',
|
||||
'agrave':'a', 'aacute':'a', 'acirc':'a', 'atilde':'a', 'auml':'a', 'aring':'a',
|
||||
'egrave':'e', 'eacute':'e', 'ecirc':'e', 'euml':'e',
|
||||
'igrave':'i', 'iacute':'i', 'icirc':'i', 'iuml':'i',
|
||||
'ograve':'o', 'oacute':'o', 'ocirc':'o', 'otilde':'o', 'ouml':'o',
|
||||
'ugrave':'u', 'uacute':'u', 'ucirc':'u', 'uuml':'u'}
|
||||
|
||||
unifiable_n = {}
|
||||
|
||||
for k in unifiable.keys():
|
||||
unifiable_n[name2cp(k)] = unifiable[k]
|
||||
|
||||
def charref(name):
|
||||
if name[0] in ['x','X']:
|
||||
c = int(name[1:], 16)
|
||||
else:
|
||||
c = int(name)
|
||||
|
||||
if not UNICODE_SNOB and c in unifiable_n.keys():
|
||||
return unifiable_n[c]
|
||||
else:
|
||||
return unichr(c)
|
||||
|
||||
def entityref(c):
|
||||
if not UNICODE_SNOB and c in unifiable.keys():
|
||||
return unifiable[c]
|
||||
else:
|
||||
try: name2cp(c)
|
||||
except KeyError: return "&" + c
|
||||
else: return unichr(name2cp(c))
|
||||
|
||||
def replaceEntities(s):
|
||||
s = s.group(1)
|
||||
if s[0] == "#":
|
||||
return charref(s[1:])
|
||||
else: return entityref(s)
|
||||
|
||||
r_unescape = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
|
||||
def unescape(s):
|
||||
return r_unescape.sub(replaceEntities, s)
|
||||
|
||||
def fixattrs(attrs):
|
||||
# Fix bug in sgmllib.py
|
||||
if not attrs: return attrs
|
||||
newattrs = []
|
||||
for attr in attrs:
|
||||
newattrs.append((attr[0], unescape(attr[1])))
|
||||
return newattrs
|
||||
|
||||
### End Entity Nonsense ###
|
||||
|
||||
def onlywhite(line):
|
||||
"""Return true if the line does only consist of whitespace characters."""
|
||||
for c in line:
|
||||
if c is not ' ' and c is not ' ':
|
||||
return c is ' '
|
||||
return line
|
||||
|
||||
def optwrap(text):
|
||||
"""Wrap all paragraphs in the provided text."""
|
||||
if not BODY_WIDTH:
|
||||
return text
|
||||
|
||||
assert wrap, "Requires Python 2.3."
|
||||
result = ''
|
||||
newlines = 0
|
||||
for para in text.split("\n"):
|
||||
if len(para) > 0:
|
||||
if para[0] is not ' ' and para[0] is not '-' and para[0] is not '*':
|
||||
for line in wrap(para, BODY_WIDTH):
|
||||
result += line + "\n"
|
||||
result += "\n"
|
||||
newlines = 2
|
||||
else:
|
||||
if not onlywhite(para):
|
||||
result += para + "\n"
|
||||
newlines = 1
|
||||
else:
|
||||
if newlines < 2:
|
||||
result += "\n"
|
||||
newlines += 1
|
||||
return result
|
||||
|
||||
def hn(tag):
|
||||
if tag[0] == 'h' and len(tag) == 2:
|
||||
try:
|
||||
n = int(tag[1])
|
||||
if n in range(1, 10): return n
|
||||
except ValueError: return 0
|
||||
|
||||
class _html2text(sgmllib.SGMLParser):
|
||||
def __init__(self, out=None, baseurl=''):
|
||||
sgmllib.SGMLParser.__init__(self)
|
||||
|
||||
if out is None: self.out = self.outtextf
|
||||
else: self.out = out
|
||||
self.outtext = u''
|
||||
self.quiet = 0
|
||||
self.p_p = 0
|
||||
self.outcount = 0
|
||||
self.start = 1
|
||||
self.space = 0
|
||||
self.a = []
|
||||
self.astack = []
|
||||
self.acount = 0
|
||||
self.list = []
|
||||
self.blockquote = 0
|
||||
self.pre = 0
|
||||
self.startpre = 0
|
||||
self.lastWasNL = 0
|
||||
self.abbr_title = None # current abbreviation definition
|
||||
self.abbr_data = None # last inner HTML (for abbr being defined)
|
||||
self.abbr_list = {} # stack of abbreviations to write later
|
||||
self.baseurl = baseurl
|
||||
|
||||
def outtextf(self, s):
|
||||
self.outtext += s
|
||||
|
||||
def close(self):
|
||||
sgmllib.SGMLParser.close(self)
|
||||
|
||||
self.pbr()
|
||||
self.o('', 0, 'end')
|
||||
|
||||
return self.outtext
|
||||
|
||||
def handle_charref(self, c):
|
||||
self.o(charref(c))
|
||||
|
||||
def handle_entityref(self, c):
|
||||
self.o(entityref(c))
|
||||
|
||||
def unknown_starttag(self, tag, attrs):
|
||||
self.handle_tag(tag, attrs, 1)
|
||||
|
||||
def unknown_endtag(self, tag):
|
||||
self.handle_tag(tag, None, 0)
|
||||
|
||||
def previousIndex(self, attrs):
|
||||
""" returns the index of certain set of attributes (of a link) in the
|
||||
self.a list
|
||||
|
||||
If the set of attributes is not found, returns None
|
||||
"""
|
||||
if not attrs.has_key('href'): return None
|
||||
|
||||
i = -1
|
||||
for a in self.a:
|
||||
i += 1
|
||||
match = 0
|
||||
|
||||
if a.has_key('href') and a['href'] == attrs['href']:
|
||||
if a.has_key('title') or attrs.has_key('title'):
|
||||
if (a.has_key('title') and attrs.has_key('title') and
|
||||
a['title'] == attrs['title']):
|
||||
match = True
|
||||
else:
|
||||
match = True
|
||||
|
||||
if match: return i
|
||||
|
||||
def handle_tag(self, tag, attrs, start):
|
||||
attrs = fixattrs(attrs)
|
||||
|
||||
if hn(tag):
|
||||
self.p()
|
||||
if start: self.o(hn(tag)*"#" + ' ')
|
||||
|
||||
if tag in ['p', 'div']: self.p()
|
||||
|
||||
if tag == "br" and start: self.o(" \n")
|
||||
|
||||
if tag == "hr" and start:
|
||||
self.p()
|
||||
self.o("* * *")
|
||||
self.p()
|
||||
|
||||
if tag in ["head", "style", 'script']:
|
||||
if start: self.quiet += 1
|
||||
else: self.quiet -= 1
|
||||
|
||||
if tag in ["body"]:
|
||||
self.quiet = 0 # sites like 9rules.com never close <head>
|
||||
|
||||
if tag == "blockquote":
|
||||
if start:
|
||||
self.p(); self.o('> ', 0, 1); self.start = 1
|
||||
self.blockquote += 1
|
||||
else:
|
||||
self.blockquote -= 1
|
||||
self.p()
|
||||
|
||||
if tag in ['em', 'i', 'u']: self.o("_")
|
||||
if tag in ['strong', 'b']: self.o("**")
|
||||
if tag == "code" and not self.pre: self.o('`') #TODO: `` `this` ``
|
||||
if tag == "abbr":
|
||||
if start:
|
||||
attrsD = {}
|
||||
for (x, y) in attrs: attrsD[x] = y
|
||||
attrs = attrsD
|
||||
|
||||
self.abbr_title = None
|
||||
self.abbr_data = ''
|
||||
if attrs.has_key('title'):
|
||||
self.abbr_title = attrs['title']
|
||||
else:
|
||||
if self.abbr_title != None:
|
||||
self.abbr_list[self.abbr_data] = self.abbr_title
|
||||
self.abbr_title = None
|
||||
self.abbr_data = ''
|
||||
|
||||
if tag == "a":
|
||||
if start:
|
||||
attrsD = {}
|
||||
for (x, y) in attrs: attrsD[x] = y
|
||||
attrs = attrsD
|
||||
if attrs.has_key('href') and not (SKIP_INTERNAL_LINKS and attrs['href'].startswith('#')):
|
||||
self.astack.append(attrs)
|
||||
self.o("[")
|
||||
else:
|
||||
self.astack.append(None)
|
||||
else:
|
||||
if self.astack:
|
||||
a = self.astack.pop()
|
||||
if a:
|
||||
i = self.previousIndex(a)
|
||||
if i is not None:
|
||||
a = self.a[i]
|
||||
else:
|
||||
self.acount += 1
|
||||
a['count'] = self.acount
|
||||
a['outcount'] = self.outcount
|
||||
self.a.append(a)
|
||||
self.o("][" + `a['count']` + "]")
|
||||
|
||||
if tag == "img" and start:
|
||||
attrsD = {}
|
||||
for (x, y) in attrs: attrsD[x] = y
|
||||
attrs = attrsD
|
||||
if attrs.has_key('src'):
|
||||
attrs['href'] = attrs['src']
|
||||
alt = attrs.get('alt', '')
|
||||
i = self.previousIndex(attrs)
|
||||
if i is not None:
|
||||
attrs = self.a[i]
|
||||
else:
|
||||
self.acount += 1
|
||||
attrs['count'] = self.acount
|
||||
attrs['outcount'] = self.outcount
|
||||
self.a.append(attrs)
|
||||
self.o("![")
|
||||
self.o(alt)
|
||||
self.o("]["+`attrs['count']`+"]")
|
||||
|
||||
if tag == 'dl' and start: self.p()
|
||||
if tag == 'dt' and not start: self.pbr()
|
||||
if tag == 'dd' and start: self.o(' ')
|
||||
if tag == 'dd' and not start: self.pbr()
|
||||
|
||||
if tag in ["ol", "ul"]:
|
||||
if start:
|
||||
self.list.append({'name':tag, 'num':0})
|
||||
else:
|
||||
if self.list: self.list.pop()
|
||||
|
||||
self.p()
|
||||
|
||||
if tag == 'li':
|
||||
if start:
|
||||
self.pbr()
|
||||
if self.list: li = self.list[-1]
|
||||
else: li = {'name':'ul', 'num':0}
|
||||
self.o(" "*len(self.list)) #TODO: line up <ol><li>s > 9 correctly.
|
||||
if li['name'] == "ul": self.o("* ")
|
||||
elif li['name'] == "ol":
|
||||
li['num'] += 1
|
||||
self.o(`li['num']`+". ")
|
||||
self.start = 1
|
||||
else:
|
||||
self.pbr()
|
||||
|
||||
if tag in ["table", "tr"] and start: self.p()
|
||||
if tag == 'td': self.pbr()
|
||||
|
||||
if tag == "pre":
|
||||
if start:
|
||||
self.startpre = 1
|
||||
self.pre = 1
|
||||
else:
|
||||
self.pre = 0
|
||||
self.p()
|
||||
|
||||
def pbr(self):
|
||||
if self.p_p == 0: self.p_p = 1
|
||||
|
||||
def p(self): self.p_p = 2
|
||||
|
||||
def o(self, data, puredata=0, force=0):
|
||||
if self.abbr_data is not None: self.abbr_data += data
|
||||
|
||||
if not self.quiet:
|
||||
if puredata and not self.pre:
|
||||
data = re.sub('\s+', ' ', data)
|
||||
if data and data[0] == ' ':
|
||||
self.space = 1
|
||||
data = data[1:]
|
||||
if not data and not force: return
|
||||
|
||||
if self.startpre:
|
||||
#self.out(" :") #TODO: not output when already one there
|
||||
self.startpre = 0
|
||||
|
||||
bq = (">" * self.blockquote)
|
||||
if not (force and data and data[0] == ">") and self.blockquote: bq += " "
|
||||
|
||||
if self.pre:
|
||||
bq += " "
|
||||
data = data.replace("\n", "\n"+bq)
|
||||
|
||||
if self.start:
|
||||
self.space = 0
|
||||
self.p_p = 0
|
||||
self.start = 0
|
||||
|
||||
if force == 'end':
|
||||
# It's the end.
|
||||
self.p_p = 0
|
||||
self.out("\n")
|
||||
self.space = 0
|
||||
|
||||
|
||||
if self.p_p:
|
||||
self.out(('\n'+bq)*self.p_p)
|
||||
self.space = 0
|
||||
|
||||
if self.space:
|
||||
if not self.lastWasNL: self.out(' ')
|
||||
self.space = 0
|
||||
|
||||
if self.a and ((self.p_p == 2 and LINKS_EACH_PARAGRAPH) or force == "end"):
|
||||
if force == "end": self.out("\n")
|
||||
|
||||
newa = []
|
||||
for link in self.a:
|
||||
if self.outcount > link['outcount']:
|
||||
self.out(" ["+`link['count']`+"]: " + urlparse.urljoin(self.baseurl, link['href']))
|
||||
if link.has_key('title'): self.out(" ("+link['title']+")")
|
||||
self.out("\n")
|
||||
else:
|
||||
newa.append(link)
|
||||
|
||||
if self.a != newa: self.out("\n") # Don't need an extra line when nothing was done.
|
||||
|
||||
self.a = newa
|
||||
|
||||
if self.abbr_list and force == "end":
|
||||
for abbr, definition in self.abbr_list.items():
|
||||
self.out(" *[" + abbr + "]: " + definition + "\n")
|
||||
|
||||
self.p_p = 0
|
||||
self.out(data)
|
||||
self.lastWasNL = data and data[-1] == '\n'
|
||||
self.outcount += 1
|
||||
|
||||
def handle_data(self, data):
|
||||
if r'\/script>' in data: self.quiet -= 1
|
||||
self.o(data, 1)
|
||||
|
||||
def unknown_decl(self, data): pass
|
||||
|
||||
def wrapwrite(text): sys.stdout.write(text.encode('utf8'))
|
||||
|
||||
def html2text_file(html, out=wrapwrite, baseurl=''):
|
||||
h = _html2text(out, baseurl)
|
||||
h.feed(html)
|
||||
h.feed("")
|
||||
return h.close()
|
||||
|
||||
def html2text(html, baseurl=''):
|
||||
return optwrap(html2text_file(html, None, baseurl))
|
||||
|
||||
if __name__ == "__main__":
|
||||
baseurl = ''
|
||||
if sys.argv[1:]:
|
||||
arg = sys.argv[1]
|
||||
if arg.startswith('http://'):
|
||||
baseurl = arg
|
||||
j = urllib.urlopen(baseurl)
|
||||
try:
|
||||
from feedparser import _getCharacterEncoding as enc
|
||||
except ImportError:
|
||||
enc = lambda x, y: ('utf-8', 1)
|
||||
text = j.read()
|
||||
encoding = enc(j.headers, text)[0]
|
||||
if encoding == 'us-ascii': encoding = 'utf-8'
|
||||
data = text.decode(encoding)
|
||||
|
||||
else:
|
||||
encoding = 'utf8'
|
||||
if len(sys.argv) > 2:
|
||||
encoding = sys.argv[2]
|
||||
data = open(arg, 'r').read().decode(encoding)
|
||||
else:
|
||||
data = sys.stdin.read().decode('utf8')
|
||||
wrapwrite(html2text(data, baseurl))
|
||||
@@ -25,6 +25,7 @@ import zipdir
|
||||
import html_constants
|
||||
from constants import *
|
||||
|
||||
import html2text
|
||||
|
||||
|
||||
class FanficWriter:
|
||||
@@ -37,6 +38,22 @@ class FanficWriter:
|
||||
def finalise(self):
|
||||
pass
|
||||
|
||||
class TextWriter(FanficWriter):
|
||||
htmlWriter = None
|
||||
|
||||
def __init__(self, base, name, author, inmemory=False, compress=False):
|
||||
self.htmlWriter = HTMLWriter(base, name, author, True, False)
|
||||
|
||||
def writeChapter(self, title, text):
|
||||
self.htmlWriter.writeChapter(title, text)
|
||||
|
||||
def finalise(self):
|
||||
self.htmlWriter.finalise()
|
||||
self.output = StringIO.StringIO()
|
||||
self.output.write(html2text.html2text(self.htmlWriter.output.getvalue().decode('utf-8')).encode('utf-8'))
|
||||
self.name = self.htmlWriter.name
|
||||
|
||||
|
||||
class HTMLWriter(FanficWriter):
|
||||
body = ''
|
||||
|
||||
@@ -59,10 +76,17 @@ class HTMLWriter(FanficWriter):
|
||||
|
||||
self.xhtmlTemplate = string.Template(html_constants.XHTML_START)
|
||||
self.chapterStartTemplate = string.Template(html_constants.XHTML_CHAPTER_START)
|
||||
|
||||
|
||||
def _printableVersion(self, text):
|
||||
try:
|
||||
d = text.decode('utf-8')
|
||||
return d
|
||||
except:
|
||||
return text
|
||||
|
||||
def writeChapter(self, title, text):
|
||||
title = title.decode('utf-8')
|
||||
text = text.decode('utf-8')
|
||||
title = self._printableVersion(title) #title.decode('utf-8')
|
||||
text = self._printableVersion(text) #text.decode('utf-8')
|
||||
self.body = self.body + '\n' + self.chapterStartTemplate.substitute({'chapter' : title})
|
||||
self.body = self.body + '\n' + text
|
||||
|
||||
|
||||
+134
@@ -0,0 +1,134 @@
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
import shutil
|
||||
import os.path
|
||||
import urllib as u
|
||||
import logging
|
||||
import pprint as pp
|
||||
import unittest
|
||||
import urllib2 as u2
|
||||
import urlparse as up
|
||||
import BeautifulSoup as bs
|
||||
import htmlentitydefs as hdefs
|
||||
|
||||
from adapter import *
|
||||
import twipassword
|
||||
|
||||
class Twilighted(FanfictionSiteAdapter):
|
||||
def __init__(self, url):
|
||||
self.url = url
|
||||
parsedUrl = up.urlparse(url)
|
||||
self.host = parsedUrl.netloc
|
||||
self.path = parsedUrl.path
|
||||
self.opener = u2.build_opener(u2.HTTPCookieProcessor())
|
||||
self.password=twipassword.password
|
||||
self.login='sigizmund'
|
||||
logging.debug("Created Twilighted: url=%s" % (self.url))
|
||||
|
||||
|
||||
def requiresLogin(self, url = None):
|
||||
return True
|
||||
|
||||
def performLogin(self, url = None):
|
||||
data = {}
|
||||
|
||||
data['penname'] = self.login
|
||||
data['password'] = self.password
|
||||
data['cookiecheck'] = '1'
|
||||
data['submit'] = 'Submit'
|
||||
|
||||
urlvals = u.urlencode(data)
|
||||
loginUrl = 'http://' + self.host + self._getLoginScript()
|
||||
logging.debug("Will now login to URL %s" % loginUrl)
|
||||
|
||||
req = self.opener.open(loginUrl, urlvals)
|
||||
|
||||
d = req.read().decode('utf-8')
|
||||
|
||||
if self.reqLoginData(d) :
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
|
||||
def setLogin(self, login):
|
||||
self.login = login
|
||||
|
||||
def setPassword(self, password):
|
||||
self.password = password
|
||||
|
||||
def extractIndividualUrls(self):
|
||||
data = self.opener.open(self.url).read()
|
||||
|
||||
if self.reqLoginData(data):
|
||||
self.performLogin()
|
||||
data = self.opener.open(self.url).read()
|
||||
if self.reqLoginData(data):
|
||||
return None
|
||||
|
||||
soup = bs.BeautifulStoneSoup(data)
|
||||
|
||||
title = soup.find('title').string
|
||||
self.storyName = title.split(' by ')[0].strip()
|
||||
self.authorName = title.split(' by ')[1].strip()
|
||||
|
||||
select = soup.find('select', { 'name' : 'chapter' } )
|
||||
|
||||
allOptions = select.findAll('option')
|
||||
result = []
|
||||
for o in allOptions:
|
||||
url = self.url + "&chapter=%s" % o['value']
|
||||
title = o.string
|
||||
result.append((url,title))
|
||||
|
||||
return result
|
||||
|
||||
def getStoryName(self):
|
||||
return self.storyName
|
||||
|
||||
def getAuthorName(self):
|
||||
return self.authorName
|
||||
|
||||
def getText(self, url):
|
||||
if url.find('http://') == -1:
|
||||
url = 'http://' + self.host + '/' + url
|
||||
|
||||
logging.debug('Getting data from: %s' % url)
|
||||
|
||||
data = self.opener.open(url).read()
|
||||
|
||||
soup = bs.BeautifulStoneSoup(data, convertEntities=bs.BeautifulStoneSoup.HTML_ENTITIES)
|
||||
|
||||
div = soup.find('div', {'id' : 'story'})
|
||||
|
||||
if None == div:
|
||||
return '<html/>'
|
||||
|
||||
return div.prettify()
|
||||
|
||||
def _getLoginScript(self):
|
||||
return '/user.php?action=login'
|
||||
|
||||
def reqLoginData(self, data):
|
||||
if data.find('Registered Users Only. Please click OK to login or register.') != -1 or data.find('There is no such account on our website') != -1:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
|
||||
class Twilighted_UnitTests(unittest.TestCase):
|
||||
def setUp(self):
|
||||
logging.basicConfig(level=logging.DEBUG)
|
||||
pass
|
||||
|
||||
def testLoginWorks(self):
|
||||
url = 'http://www.twilighted.net/viewstory.php?sid=10004'
|
||||
self.assertTrue(Twilighted(url).performLogin())
|
||||
|
||||
def testGetUrlsWorks(self):
|
||||
url = 'http://www.twilighted.net/viewstory.php?sid=10004'
|
||||
self.assertEquals(32, len(Twilighted(url).extractIndividualUrls()))
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user