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 save_pic(url,path):
searchname = '.*/(.*?.jpg)'
name = re.findall(searchname,url)
filename = path +'/'+ name[0]
#print filename + ':start'
while True:
if os.path.exists(filename):
#os.remove(filename)
errorReport.errorFileExist(filename)
print filename,' exists, skip'
return True
elif os.path.exists(filename):
os.mknod(filename)
if download(url,filename):
break
print filename + ':over'
errorReport.success(filename)
conn = urllib2.urlopen(url,data=None,timeout=5)
html = conn.read()
return html
except Exception:
errorReport.errorLoadUrl(url)
return ''
def meizi(url,path):
reTagContent = '<div.*?class="tags">.*?<span>(.*?)</span>'
reTagUrl = '<a.*?href="(.*?)".*?>'
print 'start open meiziwang'
html = ''
while True:
html = loadurl(url)
if html == '':
print 'load', url,'error'
continue
else:
break
tagContent = re.findall(reTagContent, html, re.S)
taglists = re.findall(reTagUrl, tagContent[0], re.S)
taglists = sorted(list(set(taglists)))
print 'open meiziwang over'
#print len(taglists)
for url in taglists:
meizi_series_nextpage.nextpage(url,path)
#meizi_series_getpage.tag_series(url,path)
#print url
meizi('http://www.meizitu.com','/home/hus/Desktop/meizi')
errorReport.success('/home/hus/Desktop/meizi')
print 'All over success and false has been report with txt file'