manga/mrnet.py

   1 import bs4
   2 from urllib.parse import urljoin
   3 from . import lib, htcache
   4 soup = bs4.BeautifulSoup
   5 soupify = lambda cont: soup(cont, "html.parser")
   6
   7 class page(lib.page):
   8     def __init__(self, chapter, stack, n, url):
   9         self.stack = stack
  10         self.chapter = chapter
  11         self.manga = chapter.manga
  12         self.n = n
  13         self.id = str(n)
  14         self.name = "Page %s" % n
  15         self.url = url
  16         self.ciurl = None
  17
  18     def iurl(self):
  19         if self.ciurl is None:
  20             page = soupify(htcache.fetch(self.url))
  21             self.ciurl = page.find("div", id="imgholder").find("img", id="img")["src"]
  22         return self.ciurl
  23
  24     def open(self):
  25         return lib.stdimgstream(self.iurl())
  26
  27     def __str__(self):
  28         return self.name
  29
  30     def __repr__(self):
  31         return "<mrnet.page %r.%r.%r>" % (self.manga.name, self.chapter.name, self.name)
  32
  33 class chapter(lib.pagelist):
  34     def __init__(self, manga, stack, id, name, url):
  35         self.stack = stack
  36         self.manga = manga
  37         self.id = id
  38         self.name = name
  39         self.url = url
  40         self.cpag = None
  41
  42     def __getitem__(self, i):
  43         return self.pages()[i]
  44
  45     def __len__(self):
  46         return len(self.pages())
  47
  48     def pages(self):
  49         if self.cpag is None:
  50             pg = soupify(htcache.fetch(self.url))
  51             pag = []
  52             for opt in pg.find("div", id="selectpage").find("select", id="pageMenu").findAll("option"):
  53                 url = urljoin(self.url, opt["value"])
  54                 n = int(opt.string)
  55                 pag.append(page(self, self.stack + [(self, len(pag))], n, url))
  56             self.cpag = pag
  57         return self.cpag
  58
  59     def __str__(self):
  60         return self.name
  61
  62     def __repr__(self):
  63         return "<mrnet.chapter %r.%r>" % (self.manga.name, self.name)
  64
  65 class manga(lib.manga):
  66     def __init__(self, lib, id, name, url):
  67         self.lib = lib
  68         self.id = id
  69         self.name = name
  70         self.url = url
  71         self.cch = None
  72         self.stack = []
  73
  74     def __getitem__(self, i):
  75         return self.ch()[i]
  76
  77     def __len__(self):
  78         return len(self.ch())
  79
  80     def ch(self):
  81         if self.cch is None:
  82             page = soupify(htcache.fetch(self.url))
  83             cls = page.find("div", id="chapterlist").find("table", id="listing")
  84             i = 0
  85             cch = []
  86             for tr in cls.findAll("tr"):
  87                 td = tr.find("td")
  88                 if td is None: continue
  89                 cla = td.find("a")
  90                 url = urljoin(self.url, cla["href"])
  91                 cid = name = cla.string
  92                 if isinstance(cla.nextSibling, str):
  93                     ncont = str(cla.nextSibling)
  94                     if len(ncont) > 3 and ncont[:3] == " : ":
  95                         name += ": " + 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"]
 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, urljoin(self.base, url))
 133
 134     def byname(self, prefix):
 135         prefix = prefix.lower()
 136         for manga in self:
 137             if manga.name.lower()[:len(prefix)] == prefix:
 138                 yield manga
 139
 140     def search(self, expr):
 141         expr = expr.lower()
 142         for manga in self:
 143             if expr in manga.name.lower():
 144                 yield manga