manga/mrnet.py

   1 import BeautifulSoup, urlparse
   2 import lib, htcache
   3 soup = BeautifulSoup.BeautifulSoup
   4 soupify = lambda cont: soup(cont, convertEntities=soup.HTML_ENTITIES)
   5
   6 class page(lib.page):
   7     def __init__(self, chapter, stack, n, url):
   8         self.stack = stack
   9         self.chapter = chapter
  10         self.manga = chapter.manga
  11         self.n = n
  12         self.id = str(n)
  13         self.name = u"Page %s" % n
  14         self.url = url
  15         self.ciurl = None
  16
  17     def iurl(self):
  18         if self.ciurl is None:
  19             page = soupify(htcache.fetch(self.url))
  20             self.ciurl = page.find("div", id="imgholder").find("img", id="img")["src"].encode("us-ascii")
  21         return self.ciurl
  22
  23     def open(self):
  24         return lib.stdimgstream(self.iurl())
  25
  26     def __str__(self):
  27         return self.name
  28
  29     def __repr__(self):
  30         return "<mrnet.page %r.%r.%r>" % (self.manga.name, self.chapter.name, self.name)
  31
  32 class chapter(lib.pagelist):
  33     def __init__(self, manga, stack, id, name, url):
  34         self.stack = stack
  35         self.manga = manga
  36         self.id = id
  37         self.name = name
  38         self.url = url
  39         self.cpag = None
  40
  41     def __getitem__(self, i):
  42         return self.pages()[i]
  43
  44     def __len__(self):
  45         return len(self.pages())
  46
  47     def pages(self):
  48         if self.cpag is None:
  49             pg = soupify(htcache.fetch(self.url))
  50             pag = []
  51             for opt in pg.find("div", id="selectpage").find("select", id="pageMenu").findAll("option"):
  52                 url = urlparse.urljoin(self.url, opt["value"].encode("us-ascii"))
  53                 n = int(opt.string)
  54                 pag.append(page(self, self.stack + [(self, len(pag))], n, url))
  55             self.cpag = pag
  56         return self.cpag
  57
  58     def __str__(self):
  59         return self.name
  60
  61     def __repr__(self):
  62         return "<mrnet.chapter %r.%r>" % (self.manga.name, self.name)
  63
  64 class manga(lib.manga):
  65     def __init__(self, lib, id, name, url):
  66         self.lib = lib
  67         self.id = id
  68         self.name = name
  69         self.url = url
  70         self.cch = None
  71         self.stack = []
  72
  73     def __getitem__(self, i):
  74         return self.ch()[i]
  75
  76     def __len__(self):
  77         return len(self.ch())
  78
  79     def ch(self):
  80         if self.cch is None:
  81             page = soupify(htcache.fetch(self.url))
  82             cls = page.find("div", id="chapterlist").find("table", id="listing")
  83             i = 0
  84             cch = []
  85             for tr in cls.findAll("tr"):
  86                 td = tr.find("td")
  87                 if td is None: continue
  88                 cla = td.find("a")
  89                 url = urlparse.urljoin(self.url, cla["href"].encode("us-ascii"))
  90                 name = cla.string
  91                 cid = name.encode("utf8")
  92                 if isinstance(cla.nextSibling, unicode):
  93                     ncont = unicode(cla.nextSibling)
  94                     if len(ncont) > 3 and ncont[:3] == u" : ":
  95                         name += u": " + ncont[3:]
  96                 cch.append(chapter(self, [(self, len(cch))], cid, name, url))
  97             self.cch = cch
  98         return self.cch
  99
 100     def __str__(self):
 101         return self.name
 102
 103     def __repr__(self):
 104         return "<mrnet.manga %r>" % self.name
 105
 106 class library(lib.library):
 107     def __init__(self):
 108         self.base = "http://www.mangareader.net/"
 109
 110     def byid(self, id):
 111         url = self.base + id
 112         page = soupify(htcache.fetch(url))
 113         if page.find("h2", attrs={"class": "aname"}) is None:
 114             raise KeyError(id)
 115         name = page.find("h2", attrs={"class": "aname"}).string
 116         return manga(self, id, name, url)
 117
 118     def __iter__(self):
 119         page = soupify(htcache.fetch(self.base + "alphabetical"))
 120         for sec in page.findAll("div", attrs={"class": "series_alpha"}):
 121             for li in sec.find("ul", attrs={"class": "series_alpha"}).findAll("li"):
 122                 url = li.a["href"].encode("us-ascii")
 123                 name = li.a.string
 124                 if url[:1] != "/": continue
 125                 id = url[1:]
 126                 if '/' in id:
 127                     # Does this distinction mean something?
 128                     id = id[id.rindex('/') + 1:]
 129                     if id[-5:] != ".html":
 130                         continue
 131                     id = id[:-5]
 132                 yield manga(self, id, name, urlparse.urljoin(self.base, url))
 133
 134     def byname(self, prefix):
 135         if not isinstance(prefix, unicode):
 136             prefix = prefix.decode("utf8")
 137         prefix = prefix.lower()
 138         for manga in self:
 139             if manga.name.lower()[:len(prefix)] == prefix:
 140                 yield manga
 141
 142     def search(self, expr):
 143         if not isinstance(expr, unicode):
 144             expr = expr.decode("utf8")
 145         expr = expr.lower()
 146         for manga in self:
 147             if expr in manga.name.lower():
 148                 yield manga