X-Git-Url: http://dolda2000.com/gitweb/?a=blobdiff_plain;f=manga%2Fmangafox.py;h=c254a9d9f5d94e0f30207f5425d1d3068e9b9f46;hb=0cddd237ff8cdf718379d8c9c2bc35053cf2d701;hp=ed40efb1636a3f3bd1cd07a13415b55803011831;hpb=75732d5a659e0faa04b7bb0dee367387438c05ba;p=automanga.git diff --git a/manga/mangafox.py b/manga/mangafox.py index ed40efb..c254a9d 100644 --- a/manga/mangafox.py +++ b/manga/mangafox.py @@ -1,13 +1,21 @@ -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"] - self.clen = int(self.bk.info()["Content-Length"]) + 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() @@ -109,6 +117,8 @@ def nextel(el): 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 @@ -146,9 +156,13 @@ class manga(lib.manga): 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])) + vol.ch.append(chapter(vol, vol.stack + [(vol, o)], chid, name, url)) cvol.append(vol) self.cvol = cvol return self.cvol @@ -219,6 +233,14 @@ class library(lib.library): 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))