urllib2.HTTPError: HTTP Error 400: Bad Request

 1 import urllib2
 2 import re
 3 import os
 4  
 5 def process_item(self, item, spider):
 6         headers = {
 7                     "Host":    'img31.mtime.cn',
 8                     "User-Agent":    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:53.0) Gecko/20100101 Firefox/53.0',
 9                     "Accept":    'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
10                     "Accept-Language":   'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
11                     "Accept-Encoding":    'gzip, deflate',
12                     "Connection":    'keep-alive',
13                     "Upgrade-Insecure-Requests": "1",          
14                 }
15         
16         req = urllib2.Request(url=item['addr'], headers=headers) 
17         res = urllib2.urlopen(req)
18 
19         saveFilePath = os.path.join(os.path.curdir, "down_pic", item['name'].split("_")[0]+"_"+str(item["picCount"]))
20         if os.path.exists(saveFilePath):
21             pass
22         else:
23             #os.mkdir(saveFilePath) #只能建单层文件夹
24             os.makedirs(saveFilePath)
25         file_name = os.path.join(saveFilePath, item['name'] + '.jpg')
26         with open(file_name, 'wb') as fp:
27             fp.write(res.read())
28         with open("./savePath.txt", "a") as fh:
29             fh.write(file_name+"\n")

 用urllib2抓取图片的时候，部分request报HTTP Error 400: Bad Request

参照：https://stackoverflow.com/questions/8840303/urllib2-http-error-400-bad-request?answertab=active#tab-top

because you aren't escaping the string for a URL.

改用requests成功解决问题。

 1 import os
 2 import requests 
 3 
 4  def process_item(self, item, spider):
 5         headers = {
 6                     "Host":    'img31.mtime.cn',
 7                     "User-Agent":    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:53.0) Gecko/20100101 Firefox/53.0',
 8                     "Accept":    'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
 9                     "Accept-Language":   'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
10                     "Accept-Encoding":    'gzip, deflate',
11                     "Connection":    'keep-alive',
12                     "Upgrade-Insecure-Requests": "1",          
13                 }
14         
15         res = requests.get(item['addr'], headers=headers)
16         #print res
17         #print res.url
18         #print res.headers
19         #print res.content 二进制数据
20         
21         saveFilePath = os.path.join(os.path.curdir, "down_pic", item['name'].split("_")[0]+"_"+str(item["picCount"]))
22         if os.path.exists(saveFilePath):
23             pass
24         else:
25             #os.mkdir(saveFilePath) #只能建单层文件夹
26             os.makedirs(saveFilePath)
27         file_name = os.path.join(saveFilePath, item['name'] + '.jpg')
28         with open(file_name, 'wb') as fp:
29             fp.write(res.content)
30         with open("./savePath.txt", "a") as fh:
31             fh.write(file_name+"\n")

 

转载于:https://www.cnblogs.com/v-BigdoG-v/p/7436402.html