之前看了好几遍的 python语法,这一阵忙完开始复习.import re
import urllib.request
from urllib.error import URLError,HTTPError
import sys
if name == 'main':
url = "http://www.qiushibaike.com/imgrank/page/1"
user_angent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = {
'Connection': 'Keep-Alive',
'Accept': 'text/html, application/xhtml+xml, /',
'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko'
}
j=0
for i in range(1,11+1):
try:
url = re.sub('page/\d+','page/%d' % i,url,re.S)
print(url)
re = urllib.request.Request(url,headers=headers)
response = urllib.request.urlopen(re,timeout=10)
items1 = re.findall('<div class="article block untagged mb15" id=(.*?)<div class="stats"', response.read().decode('utf-8'), re.S)
print(items1)
except HTTPError as e:
print("eee")
© 著作权归作者所有
文章评论(0)