def picurl(url,path):
if os.path.exists(path):
print path, 'exist'
else:
os.makedirs(path)
html = ''
while True:
html = loadurl(url)
if html == '':
print 'load', url,'error'
continue
else:
break
#conn = urllib2.urlopen(url,data=None,timeout=2)
#html = conn.read()
rePicContent1 = '<div.*?id="picture.*?>.*?<p>(.*?)</p>'
rePicContent2 = '<div.*?class="postContent.*?>.*?<p>(.*?)</p>'
rePicList = '<img.*?src="(.*?)".*?>'
picContent = re.findall(rePicContent1, html,re.S)
if len(picContent) <=0:
errorReport.errorIndex(url, rePicContent1)
picContent = re.findall(rePicContent2, html,re.S)
if len(picContent) <=0:
errorReport.errorIndex(url, rePicContent2)
print 'load false, over download this page and return'
return False
else:
picList = re.findall(rePicList,picContent[0],re.S)
pic_list(picList,path)
#url = 'http://www.meizitu.com/a/454.html'
#picurl(url,'/home/hus/Desktop/demo')
def oneOfSeries(urllist,path):
searchname = '.*/(.*?).html'
current_path = ''
for url in urllist:
try:
name = re.findall(searchname,url,re.S)
current_path = path + '/' + name[0]
meizi_page_download.picurl(url,current_path)
errorReport.success(url)
except IndexError:
errorReport.errorIndex(url, searchname)
def tag_series(url,path):
#searchname = '.*/(.*?).html'
#name = re.findall(searchname,url,re.S)
#path = path + '/' + name[0]
reSeriesList = '<div .*?class="pic".*?>.*?<a.*?href="(.*?)".*?target.*?>'
html = ''
while True:
html = loadurl(url)
if html == '':
print 'load', url,'error'
continue
else:
break
seriesList = re.findall(reSeriesList,html,re.S)
if len(seriesList) ==0:
errorReport.errorIndex(url, reSeriesList)
else:
oneOfSeries(seriesList,path)
#tag_series('http://www.meizitu.com/a/sifang.html','/home/hus/Desktop')