How to load, using python, a form containing an image?

Question

I have problems with this ...

You can get the same result as in http://i.joyton.com:2010 Using this image. and other parameters are saved by default.

def search_img(item, image_name): try: f = open(image_name, 'rb') img = f.read() print type(img) except IOError, e: print 'fail to open %s' % image_name print e return None ts = str(time.time()) m = md5.new('testsearch_by_image' + item) m.update(ts) m.update('0123456789') sign = m.hexdigest() params = urllib.urlencode( { 'item': item, 'app_key': 'test', 'cmd':'search_by_image', 'sign':sign, 'img_file':img, 'extra':'', 'time_stamp':ts, }) headers = {'Content-type': 'application/x-www-form-urlencode', 'Accept': 'text/plain'} conn = httplib.HTTPConnection('i.joyton.com', 2010) conn.request('POST', '', params, headers) response = conn.getresponse() print response.status, response.reason print response.read() conn.close() return response.read() if __name__ == '__main__': search_img('book', 'f:\\book_001.jpg') 

Everything works fine in the browser, but my script is not. Sometimes a script returns the correct result; sometimes he gets other books, sometimes he doesn't get anything. When he receives other books, these books are usually searched by other people.

Answer 1

Here is your code modified to do multipart/form-data . Although this did not work when I tested on my PC against your URL, it probably needs to be hacked a bit (maybe the character doesn’t fit or something else) before you can get it to work.

 import mimetypes import string import random import time import md5 import httplib def upload(fields,files): boundaryChars = list(string.lowercase) + list(string.uppercase) + \ [str(x) for x in range(10)] + ['_'*10] random.shuffle(boundaryChars) boundary = '----------RaNdOm_crAPP'+''.join(boundaryChars[:20]) CRLF = '\r\n' elem = [] for key in fields: elem.append('--' + boundary) elem.append('Content-Disposition: form-data; name="%s"' % key) elem.append('') elem.append(fields[key]) for (key, filename,value) in files: elem.append('--' + boundary) elem.append('Content-Disposition: form-data; name="%s"; filename="%s"' % (key, filename)) elem.append('Content-Type: %s' % mimetypes.guess_type(filename)[0] or \ 'application/octet-stream') elem.append('') elem.append(value) elem.append('--' + boundary + '--') elem.append('') body = CRLF.join(elem) content_type = 'multipart/form-data; boundary=%s' % boundary return content_type, body def search_img(item, image_name): try: f = open(image_name, 'rb') img = f.read() except IOError, e: print 'fail to open %s' % image_name print e return None ts = str(time.time()) m = md5.new('testsearch_by_image' + item) m.update(ts) m.update('0123456789') sign = m.hexdigest() #params = urllib.urlencode( ) contentType,body = upload({ 'item': item, 'app_key': 'test', 'cmd':'search_by_image', 'sign':sign, #'img_file':img, 'extra':'', 'time_stamp':ts, }, [('img_file', image_name, img)] ) headers = { 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Content-type': contentType, 'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.56 Safari/536.5', 'Host':'i.joyton.com:2010', 'Origin':'http://i.joyton.com:2010', 'Referer':'http://i.joyton.com:2010/' } #print c #print body conn = httplib.HTTPConnection('i.joyton.com', 2010) conn.request('POST', '/', body, headers) response = conn.getresponse() print response.status, response.reason print response.read() conn.close() return response.read() if __name__ == '__main__': search_img('book', 'iMgXS.jpg') #the same image.