def downloadImg(id,url):
global WHERE
global SQLS
WHERE+=1
#print WHERE,"条记录以入库"
url="http://www.google.com/searchbyimage?image_url="+url
print url
res=Gzzip.newOpen(url)
r=res.read()
#print r
#print res.headers
pattern=r'initialize\((.*?)\)'
url=re.findall(pattern,r,re.MULTILINE|re.S)
url=url[0].replace('/search','http://www.google.com/search').replace('\\x','%')
#print url
url=urllib2.unquote(url).replace('&','&')
#delete ''
url=url[1:-1]
r=Gzzip.newOpen(url).read()
pattern=r'italic">(.*?)</a'
title=re.findall(pattern,r,re.MULTILINE|re.S)
if len(title)==0:
title=['no title']
SQLS="UPDATE `spider` SET `is_named`=1,`title`='"+re.escape(title[0])+"' WHERE `id`="+str(id)+";"
try:
print SQLS
res=cursor.execute(SQLS)
except Exception:
pass
f.write(SQLS)
def pageContent(url):
r=Gzzip.newOpen("http://www.imgspark.com"+url)
src=[]
#src
pattern=r'id="lrg_image" src="(.*?)"'
src.append(re.findall(pattern,r,re.MULTILINE|re.S)[0])
#location
pattern=r'<span id="source_content"><a href="(.*?)"'
try:
src.append(re.findall(pattern,r,re.MULTILINE|re.S)[0])
except Exception:
if len(src)==1:
src.append('None')
#tags
pattern=r'<ul class="list_tags_horizontal">(.*?)</ul>'
res=re.findall(pattern,r,re.MULTILINE|re.S)
pattern=r'title="(.*?)"'
tags=re.findall(pattern,res[0],re.MULTILINE|re.S)
src.append(tags)
return src
def listhref(id):
url="http://www.imgspark.com/image/popular/all/alltime/"+str(id)+"/"
r=Gzzip.newOpen(url)
pattern=r'<div class="image_wrap">\s+<a href="(.*?)"(?:.*?)\s+</div>'
listHrefs=re.findall(pattern,r,re.MULTILINE|re.S)
return listHrefs
