Commit | Line | Data |
---|---|---|
bbcdf86a FT |
1 | import urllib |
2 | import BeautifulSoup, urlparse | |
3 | import lib, htcache | |
4 | soup = BeautifulSoup.BeautifulSoup | |
5 | ||
6 | class imgstream(lib.imgstream): | |
7 | def __init__(self, url): | |
8 | self.bk = urllib.urlopen(url) | |
9 | ok = False | |
10 | try: | |
11 | if self.bk.getcode() != 200: | |
12 | raise IOError("Server error: " + str(self.bk.getcode())) | |
13 | self.ctype = self.bk.info()["Content-Type"] | |
14 | self.clen = int(self.bk.info()["Content-Length"]) | |
15 | ok = True | |
16 | finally: | |
17 | if not ok: | |
18 | self.bk.close() | |
19 | ||
20 | def fileno(self): | |
21 | return self.bk.fileno() | |
22 | ||
23 | def close(self): | |
24 | self.bk.close() | |
25 | ||
26 | def read(self, sz = None): | |
27 | if sz is None: | |
28 | return self.bk.read() | |
29 | else: | |
30 | return self.bk.read(sz) | |
31 | ||
32 | class page(lib.page): | |
33 | def __init__(self, chapter, stack, n, url): | |
34 | self.stack = stack | |
35 | self.chapter = chapter | |
36 | self.manga = chapter.manga | |
37 | self.n = n | |
38 | self.id = str(n) | |
39 | self.name = u"Page %s" % n | |
40 | self.url = url | |
41 | self.ciurl = None | |
42 | ||
43 | def iurl(self): | |
44 | if self.ciurl is None: | |
45 | page = soup(htcache.fetch(self.url)) | |
46 | self.ciurl = page.find("div", id="imgholder").find("img", id="img")["src"].encode("us-ascii") | |
47 | return self.ciurl | |
48 | ||
49 | def open(self): | |
50 | return imgstream(self.iurl()) | |
51 | ||
52 | def __str__(self): | |
53 | return self.name | |
54 | ||
55 | def __repr__(self): | |
56 | return "<mrnet.page %r.%r.%r>" % (self.manga.name, self.chapter.name, self.name) | |
57 | ||
58 | class chapter(lib.pagelist): | |
59 | def __init__(self, manga, stack, id, name, url): | |
60 | self.stack = stack | |
61 | self.manga = manga | |
62 | self.id = id | |
63 | self.name = name | |
64 | self.url = url | |
65 | self.cpag = None | |
66 | ||
67 | def __getitem__(self, i): | |
68 | return self.pages()[i] | |
69 | ||
70 | def __len__(self): | |
71 | return len(self.pages()) | |
72 | ||
73 | def pages(self): | |
74 | if self.cpag is None: | |
75 | pg = soup(htcache.fetch(self.url)) | |
76 | pag = [] | |
77 | for opt in pg.find("div", id="selectpage").find("select", id="pageMenu").findAll("option"): | |
78 | url = urlparse.urljoin(self.url, opt["value"].encode("us-ascii")) | |
79 | n = int(opt.string) | |
80 | pag.append(page(self, self.stack + [(self, len(pag))], n, url)) | |
81 | self.cpag = pag | |
82 | return self.cpag | |
83 | ||
84 | def __str__(self): | |
85 | return self.name | |
86 | ||
87 | def __repr__(self): | |
88 | return "<mrnet.chapter %r.%r>" % (self.manga.name, self.name) | |
89 | ||
90 | class manga(lib.manga): | |
91 | def __init__(self, lib, id, name, url): | |
92 | self.lib = lib | |
93 | self.id = id | |
94 | self.name = name | |
95 | self.url = url | |
96 | self.cch = None | |
97 | self.stack = [] | |
98 | ||
99 | def __getitem__(self, i): | |
100 | return self.ch()[i] | |
101 | ||
102 | def __len__(self): | |
103 | return len(self.ch()) | |
104 | ||
105 | def ch(self): | |
106 | if self.cch is None: | |
107 | page = soup(htcache.fetch(self.url)) | |
108 | cls = page.find("div", id="chapterlist").find("table", id="listing") | |
109 | i = 0 | |
110 | cch = [] | |
111 | for tr in cls.findAll("tr"): | |
112 | td = tr.find("td") | |
113 | if td is None: continue | |
114 | cla = td.find("a") | |
115 | url = urlparse.urljoin(self.url, cla["href"].encode("us-ascii")) | |
116 | name = cla.string | |
117 | cid = name.encode("utf8") | |
118 | if isinstance(cla.nextSibling, unicode): | |
119 | ncont = unicode(cla.nextSibling) | |
68143b85 | 120 | if len(ncont) > 3 and ncont[:3] == u" : ": |
bbcdf86a FT |
121 | name += u": " + ncont[3:] |
122 | cch.append(chapter(self, [(self, len(cch))], cid, name, url)) | |
123 | self.cch = cch | |
124 | return self.cch | |
125 | ||
126 | def __str__(self): | |
127 | return self.name | |
128 | ||
129 | def __repr__(self): | |
130 | return "<mrnet.manga %r>" % self.name | |
131 | ||
132 | class library(lib.library): | |
133 | def __init__(self): | |
134 | self.base = "http://www.mangareader.net/" | |
135 | ||
136 | def byid(self, id): | |
137 | url = self.base + id | |
138 | page = soup(htcache.fetch(url)) | |
139 | if page.find("h2", attrs={"class": "aname"}) is None: | |
140 | raise KeyError(id) | |
141 | name = page.find("h2", attrs={"class": "aname"}).string | |
142 | return manga(self, id, name, url) | |
68143b85 FT |
143 | |
144 | def __iter__(self): | |
145 | page = soup(htcache.fetch(self.base + "alphabetical")) | |
146 | for sec in page.findAll("div", attrs={"class": "series_alpha"}): | |
147 | for li in sec.find("ul", attrs={"class": "series_alpha"}).findAll("li"): | |
148 | url = li.a["href"].encode("us-ascii") | |
149 | name = li.a.string | |
150 | if url[:1] != "/": continue | |
151 | id = url[1:] | |
152 | if '/' in id: | |
153 | # Does this distinction mean something? | |
154 | id = id[id.rindex('/') + 1:] | |
155 | if id[-5:] != ".html": | |
156 | continue | |
157 | id = id[:-5] | |
158 | yield manga(self, id, name, urlparse.urljoin(self.base, url)) | |
159 | ||
160 | def byname(self, prefix): | |
161 | if not isinstance(prefix, unicode): | |
162 | prefix = prefix.decode("utf8") | |
163 | prefix = prefix.lower() | |
164 | for manga in self: | |
165 | if manga.name.lower()[:len(prefix)] == prefix: | |
166 | yield manga |