from smthparser import BeautyArticleProcessor
from smthapi import SimpleSMTH
from url_pic_finder import *
smth = SimpleSMTH()
out = smth.get_url_data("http://www.newsmth.net/atomic.php?act=article&board=Picture&id=569616")
parser = BeautyArticleProcessor()
parser.feed(unicode(out, "gbk", "ignore"))
result = parser.getall()
print "==================="
print result["c"]
print "==================="
print result["ref"]
print "==================="
print result["sign"]
print "==================="
urls = "http://www.newsmth.net/bbscon.php" + result["pic"]
print find_url(urls)
tries=0
def login(smth):
global tries
r=smth.smthLogin(userid,userpass)
if r==0:
key=context.gen_sid()
smth.saveCj(key)
else:
print "login error"
tries=tries+1
if tries < 3:
login(smth)
smth = SimpleSMTH()
#sumaryFeeds=[]
feed=Feed()
login(smth)
#get top10 topics
out=smth.get_url_data("http://www.newsmth.net/rssi.php?h=1")
top10parser=Top10Parser(out)
articleparser=BeautyArticleProcessor()
#read data from disk
try:
f=open(archive+"/sm.data","r")
sumaryFeeds=cPickle.load(f)
print "SumaryFeeds exist"
f.close()
def down_image(smth,url,archive):
print "download image from :%s"%url
image_uid=hashlib.md5(url).hexdigest()
y=url.split("/")[2]
filename=image_uid+'.'+'jpg'
localimage='%s/images/%s' % (archive,filename)
if os.path.isfile(localimage):
print localimage+"existed"
return "images/"+filename
if os.path.isdir(archive+"/images/") == False:
os.mkdir(archive+"/images/")
imageData=smth.get_url_data(url)
try:
#im=Image.open(StringIO(imageData)).convert("L")
im=Image.open(StringIO(imageData))
#resize
width,height=im.size
im2=im.resize((width/2,height/2),Image.ANTIALIAS)
im2.save(localimage)
except:
pass
return "images/"+filename
if __name__=="__main__":
url="http://www.newsmth.net/bbscon.php?bid=382&id=570506"
smth=SimpleSMTH()
out=smth.get_url_data(url)
for imageurl in find_url(unicode(out,"gbk")):
print down_image(smth,imageurl)
from smthparser import BeautyArticleProcessor
from smthapi import SimpleSMTH
from url_pic_finder import *
smth=SimpleSMTH()
out=smth.get_url_data("http://www.newsmth.net/atomic.php?act=article&board=Picture&id=569616")
parser=BeautyArticleProcessor()
parser.feed(unicode(out,"gbk","ignore"))
result=parser.getall()
print "==================="
print result['c']
print "==================="
print result['ref']
print "==================="
print result['sign']
print "==================="
urls="http://www.newsmth.net/bbscon.php"+result['pic']
print find_url(urls)
def login(smth):
global tries
r = smth.smthLogin(userid, userpass)
if r == 0:
key = context.gen_sid()
smth.saveCj(key)
else:
print "login error"
tries = tries + 1
if tries < 3:
login(smth)
smth = SimpleSMTH()
#sumaryFeeds=[]
feed = Feed()
login(smth)
#get top10 topics
out = smth.get_url_data("http://www.newsmth.net/rssi.php?h=1")
top10parser = Top10Parser(out)
articleparser = BeautyArticleProcessor()
#read data from disk
try:
f = open(archive + "/sm.data", "r")
sumaryFeeds = cPickle.load(f)
print "SumaryFeeds exist"
f.close()
except IOError: