-import urllib
-import BeautifulSoup
+import urllib, re
+import BeautifulSoup, json
import lib, htcache
soup = BeautifulSoup.BeautifulSoup
class imgstream(lib.imgstream):
def __init__(self, url):
self.bk = urllib.urlopen(url)
- self.ctype = self.bk.info()["Content-Type"]
+ ok = False
+ try:
+ if self.bk.getcode() != 200:
+ raise IOError("Server error: " + str(self.bk.getcode()))
+ self.ctype = self.bk.info()["Content-Type"]
+ self.clen = int(self.bk.info()["Content-Length"])
+ ok = True
+ finally:
+ if not ok:
+ self.bk.close()
def fileno(self):
return self.bk.fileno()
self.manga = self.volume.manga
self.n = n
self.id = str(n)
+ self.name = u"Page %s" % n
self.url = url
self.ciurl = None
def open(self):
return imgstream(self.iurl())
+ def __str__(self):
+ return self.name
+
+ def __repr__(self):
+ return "<mangafox.page %r.%r.%r.%r>" % (self.manga.name, self.volume.name, self.chapter.name, self.name)
+
class chapter(lib.pagelist):
def __init__(self, volume, stack, id, name, url):
self.stack = stack
return el
class manga(lib.manga):
+ cure = re.compile(r"/c[\d.]+/$")
+
def __init__(self, lib, id, name, url):
self.lib = lib
self.id = id
if self.cvol is None:
page = soup(htcache.fetch(self.url))
vls = page.find("div", id="chapters").findAll("div", attrs={"class": "slide"})
- self.cvol = []
+ cvol = []
for i, vn in enumerate(reversed(vls)):
name = vn.find("h3", attrs={"class": "volume"}).contents[0].strip()
vid = name.encode("utf8")
except KeyError:
pass
url = n.a["href"].encode("us-ascii")
- if url[-7:] != "/1.html":
+ if url[-7:] == "/1.html":
+ url = url[:-6]
+ elif self.cure.search(url) is not None:
+ pass
+ else:
raise Exception("parse error: unexpected chapter URL for %r: %s" % (self, url))
- vol.ch.append(chapter(vol, vol.stack + [(vol, o)], chid, name, url[:-6]))
- self.cvol.append(vol)
+ vol.ch.append(chapter(vol, vol.stack + [(vol, o)], chid, name, url))
+ cvol.append(vol)
+ self.cvol = cvol
return self.cvol
def __str__(self):
ls = self.alphapage(pno)
i = 0
+ def search(self, expr):
+ resp = urllib.urlopen(self.base + ("ajax/search.php?term=%s" % urllib.quote(expr)))
+ try:
+ rc = json.load(resp)
+ finally:
+ resp.close()
+ return [manga(self, id.encode("utf8"), name, self.base + ("manga/%s/" % id.encode("utf8"))) for num, name, id, genres, author in rc]
+
def byid(self, id):
url = self.base + ("manga/%s/" % id)
page = soup(htcache.fetch(url))