local: Treat dots/periods as digits in destructuring directories.

[automanga.git] / manga / batoto.py

diff --git a/manga/batoto.py b/manga/batoto.py
index a7a2108..42edfac 100644 (file)
--- a/manga/batoto.py
+++ b/manga/batoto.py
@@ -38,7 +38,9 @@ def nextel(el):
             return el
 
 def fetchreader(lib, readerid, page):
-    pg = soupify(lib.sess.fetch(lib.base + "areader?" + urllib.parse.urlencode({"id": readerid, "p": str(page)}),
+    pg = soupify(lib.sess.fetch(lib.base + "areader?" + urllib.parse.urlencode({"id": readerid,
+                                                                                "p": str(page),
+                                                                                "supress_webtoon": "t"}),
                                 headers={"Referer": "http://bato.to/reader"}))
     return pg
 
@@ -67,13 +69,14 @@ class page(lib.page):
         return self.name
 
     def __repr(self):
-        return "<batoto.page %r.%r.%r>" % (self.chapter.manga.name, self.chapter.name, self.name)
+        return "<batoto.page %r.%r.%r.%r>" % (self.chapter.manga.name, self.chapter.group.name, self.chapter.name, self.name)
 
 class chapter(lib.pagelist):
-    def __init__(self, manga, stack, id, name, readerid):
+    def __init__(self, group, stack, id, name, readerid):
         self.stack = stack
-        self.manga = manga
-        self.lib = manga.lib
+        self.group = group
+        self.manga = group.manga
+        self.lib = self.manga.lib
         self.id = id
         self.name = name
         self.readerid = readerid
@@ -100,7 +103,27 @@ class chapter(lib.pagelist):
         return self.name
 
     def __repr__(self):
-        return "<batoto.chapter %r.%r>" % (self.manga.name, self.name)
+        return "<batoto.chapter %r.%r.%r>" % (self.manga.name, self.group.name, self.name)
+
+class group(lib.pagelist):
+    def __init__(self, manga, stack, id, name):
+        self.stack = stack
+        self.manga = manga
+        self.id = id
+        self.name = name
+        self.ch = []
+
+    def __getitem__(self, i):
+        return self.ch[i]
+
+    def __len__(self):
+        return len(self.ch)
+
+    def __str__(self):
+        return self.name
+
+    def __repr__(self):
+        return "<batoto.group %r.%r" % (self.manga.name, self.name)
 
 class manga(lib.manga):
     def __init__(self, lib, id, name, url):
@@ -145,12 +168,20 @@ class manga(lib.manga):
                         if m is None: raise pageerror("Got weird chapter URL: %r" % url, page)
                         readerid = m.group(1)
                         name = ch.td.a.text
-                        cch.append((readerid, name))
+                        gname = nextel(nextel(ch.td)).text.strip()
+                        cch.append((readerid, name, gname))
             cch.reverse()
-            rch = []
-            for n, (readerid, name) in enumerate(cch):
-                rch.append(chapter(self, [(self, n)], readerid, name, readerid))
-            self.cch = rch
+            groups = {}
+            for n, (readerid, name, gname) in enumerate(cch):
+                groups.setdefault(gname, [n, []])[1].append((readerid, name))
+            groups = sorted(groups.items(), key=lambda o: o[1][0])
+            rgrp = []
+            for n, (gname, (_, gch)) in enumerate(groups):
+                ngrp = group(self, [(self, n)], gname, gname)
+                for m, (readerid, name) in enumerate(gch):
+                    ngrp.ch.append(chapter(ngrp, ngrp.stack + [(ngrp, m)], readerid, name, readerid))
+                rgrp.append(ngrp)
+            self.cch = rgrp
         return self.cch
 
     def altnames(self):
@@ -245,6 +276,7 @@ class session(object):
             else:
                 return
         else:
+            pass
 
         form = page.find("form", id="login")
         if not form and pre:
@@ -257,6 +289,7 @@ class session(object):
         values["rememberMe"] = "1"
         values["anonymous"] = "1"
         req = urllib.request.Request(form["action"], urllib.parse.urlencode(values).encode("ascii"))
+        req.add_header("User-Agent", self.useragent)
         with self.web.open(req) as hs:
             page = soupify(hs.read())
         for resp in page.findAll("p", attrs={"class": "message"}):
@@ -269,8 +302,10 @@ class session(object):
     def open(self, url):
         return self.web.open(url)
 
+    useragent = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.22 (KHTML, like Gecko) Chrome/25.0.1364.160 Safari/537.22"
     def fetch(self, url, headers=None):
         req = urllib.request.Request(url)
+        req.add_header("User-Agent", self.useragent)
         if headers is not None:
             for k, v in headers.items():
                 req.add_header(k, v)
@@ -307,7 +342,9 @@ class library(lib.library):
         while True:
             _pars = dict(pars)
             _pars["p"] = str(p)
-            resp = urllib.request.urlopen(self.base + "search?" + urllib.parse.urlencode(_pars))
+            req = urllib.request.Request(self.base + "search?" + urllib.parse.urlencode(_pars))
+            req.add_header("User-Agent", session.useragent)
+            resp = urllib.request.urlopen(req)
             try:
                 page = soupify(resp.read())
             finally: