manga/mrnet.py

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