-import urllib
import BeautifulSoup, urlparse
import lib, htcache
soup = BeautifulSoup.BeautifulSoup
-
-class imgstream(lib.imgstream):
- def __init__(self, url):
- self.bk = urllib.urlopen(url)
- 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()
-
- def close(self):
- self.bk.close()
-
- def read(self, sz = None):
- if sz is None:
- return self.bk.read()
- else:
- return self.bk.read(sz)
+soupify = lambda cont: soup(cont, convertEntities=soup.HTML_ENTITIES)
class page(lib.page):
def __init__(self, chapter, stack, n, url):
def iurl(self):
if self.ciurl is None:
- page = soup(htcache.fetch(self.url))
+ page = soupify(htcache.fetch(self.url))
self.ciurl = page.find("div", id="imgholder").find("img", id="img")["src"].encode("us-ascii")
return self.ciurl
def open(self):
- return imgstream(self.iurl())
+ return lib.stdimgstream(self.iurl())
def __str__(self):
return self.name
def pages(self):
if self.cpag is None:
- pg = soup(htcache.fetch(self.url))
+ pg = soupify(htcache.fetch(self.url))
pag = []
for opt in pg.find("div", id="selectpage").find("select", id="pageMenu").findAll("option"):
url = urlparse.urljoin(self.url, opt["value"].encode("us-ascii"))
def ch(self):
if self.cch is None:
- page = soup(htcache.fetch(self.url))
+ page = soupify(htcache.fetch(self.url))
cls = page.find("div", id="chapterlist").find("table", id="listing")
i = 0
cch = []
def byid(self, id):
url = self.base + id
- page = soup(htcache.fetch(url))
+ page = soupify(htcache.fetch(url))
if page.find("h2", attrs={"class": "aname"}) is None:
raise KeyError(id)
name = page.find("h2", attrs={"class": "aname"}).string
return manga(self, id, name, url)
def __iter__(self):
- page = soup(htcache.fetch(self.base + "alphabetical"))
+ page = soupify(htcache.fetch(self.base + "alphabetical"))
for sec in page.findAll("div", attrs={"class": "series_alpha"}):
for li in sec.find("ul", attrs={"class": "series_alpha"}).findAll("li"):
url = li.a["href"].encode("us-ascii")