GET works, POST doesn't - python

I'm writing a small Python 2.x app which grabs images from URLs, converts them to base64, then submits them using requests to an API server as parameters of a POST request. My admittedly amateurish code is as follows:
import csv
import json
import requests
import base64
import getpass
f = raw_input("Enter CSV filename: ")
global clientCode
clientCode = raw_input("Enter customer code: ")
username = raw_input("Enter username: ")
password = getpass.getpass("Enter password: ")
global url
url = "https://" + clientCode + ".redacted.com/api"
def getSessionKey():
querystring = {"request":"verifyUser","username":username,"password":password,"clientCode":clientCode}
response = requests.request("GET", url, params=querystring, timeout=10)
jr = json.loads(response.text)
# print(response.text)
global sessionKey
sessionKey = jr['records'][0]['sessionKey']
errorCode = jr['status']['errorCode']
with open(f, 'rb') as myfile:
reader = csv.reader(myfile)
rownum = 0
getSessionKey()
for row in reader:
productID = row[0]
imageURL = row[1]
dlimage = requests.get(imageURL, stream=True, timeout=10)
encodedImage = base64.encodestring(dlimage.content)
imagequery = {'clientCode':clientCode,'sessionKey':sessionKey,'request':'saveProductPicture','productID':productID,'picture':encodedImage}
response = requests.post(url, data=imagequery, timeout=10)
print response.status_code
ir = json.loads(response.text)
errorCode = ir['status']['errorCode']
print errorCode
rownum = rownum + 1
Now, if I change the response line to response = requests.get(url, params=imagequery, timeout=10), it works. But since this is a GET request, the server throws an HTTP 414 error for any images larger than about 1kb. If I run the code as above, the API server gives an error which indicates it's not seeing the clientCode parameter, so it would stand to reason that it's not seeing any of the data. What am I doing wrong?
Thanks for helping me learn by doing.

I'm still not sure why requests was behaving the way it was, but I rewrote the code to use httplib instead, and it works.

Related

Error: proxy = next(proxy_pool) StopIteration

I am trying to run a script and it has a standard URL for proxies which allows the script to run fine. Once I add my own proxy URL I am getting the error Error: proxy = next(proxy_pool) StopIteration. My URL is in another file and I can also link that if needed.
Code is below, if anyone can help that would be great.
import string
import os
import requests
import proxygen
from itertools import cycle
import base64
from random import randint
N = input("How many tokens : ")
count = 0
current_path = os.path.dirname(os.path.realpath(__file__))
url = "https://discordapp.com/api/v6/users/#me/library"
while(int(count) < int(N)):
tokens = []
base64_string = "=="
while(base64_string.find("==") != -1):
sample_string = str(randint(000000000000000000, 999999999999999999))
sample_string_bytes = sample_string.encode("ascii")
base64_bytes = base64.b64encode(sample_string_bytes)
base64_string = base64_bytes.decode("ascii")
else:
token = base64_string+"."+random.choice(string.ascii_letters).upper()+''.join(random.choice(string.ascii_letters + string.digits)
for _ in range(5))+"."+''.join(random.choice(string.ascii_letters + string.digits) for _ in range(27))
count += 1
tokens.append(token)
proxies = proxygen.get_proxies()
proxy_pool = cycle(proxies)
for token in tokens:
proxy = next(proxy_pool)
header = {
"Content-Type": "application/json",
"authorization": token
}
try:
r = requests.get(url, headers=header, proxies={'https':"http://"+proxy})
print(r.text)
print(token)
if r.status_code == 200:
print(u"\u001b[32;1m[+] Token Works!\u001b[0m")
f = open(current_path+"/"+"workingtokens.txt", "a")
f.write(token+"\n")
elif "rate limited." in r.text:
print("[-] You are being rate limited.")
else:
print(u"\u001b[31m[-] Invalid Token.\u001b[0m")
except requests.exceptions.ProxyError:
print("BAD PROXY")
tokens.remove(token)
``
Try this code for get_proxies()
import requests
def get_proxies():
#in your example missing schema
url = 'https://proxy.link/list/get/5691264d3b19a600feef69dc3a27368d'
response = requests.get(url)
raw = response.text.split('\n')
proxies = set(raw)
return proxies
Output here

Cannot Process decoded Image files, Flask, OpenCV

I am receiving a bunch of images to the flask app via the client file.
client.py
# Generate the parallel requests based on the ThreadPool Executor
from concurrent.futures import ThreadPoolExecutor as PoolExecutor
import sys
import time
import glob
import requests
import threading
import uuid
import base64
import json
import os
#send http request
def call_object_detection_service(image):
try:
url = str(sys.argv[2])
data = {}
#generate uuid for image
id = uuid.uuid5(uuid.NAMESPACE_OID, image)
# Encode image into base64 string
with open (image, 'rb') as image_file:
data['image'] = base64.b64encode(image_file.read()).decode('utf-8')
data['id'] = str(id)
headers = {'Content-Type': 'application/json'}
response = requests.post(url, json= json.dumps(data), headers = headers)
if response.ok:
output = "Thread : {}, input image: {}, output:{}".format(threading.current_thread().getName(),
image, response.text)
print(output)
else:
print ("Error, response status:{}".format(response))
except Exception as e:
print("Exception in webservice call: {}".format(e))
# gets list of all images path from the input folder
def get_images_to_be_processed(input_folder):
images = []
for image_file in glob.iglob(input_folder + "*.jpg"):
images.append(image_file)
return images
def main():
## provide argumetns-> input folder, url, number of wrokers
if len(sys.argv) != 4:
raise ValueError("Arguments list is wrong. Please use the following format: {} {} {} {}".
format("python iWebLens_client.py", "<input_folder>", "<URL>", "<number_of_workers>"))
input_folder = os.path.join(sys.argv[1], "")
images = get_images_to_be_processed(input_folder)
num_images = len(images)
num_workers = int(sys.argv[3])
start_time = time.time()
#craete a worker thread to invoke the requests in parallel
with PoolExecutor(max_workers=num_workers) as executor:
for _ in executor.map(call_object_detection_service, images):
pass
#elapsed_time = time.time() - start_time
#print("Total time spent: {} average response time: {}".format(elapsed_time, elapsed_time/num_images))
if __name__ == "__main__":
main()
I decode them like so
Flask App
app = Flask(__name__)
c = 1
#app.route('/api/object_detection', methods = ['POST'])
def main():
global c
try:
data = request.get_json(force=True)
uid = data.get('id')
image = data.get('image')
print(image)
im = base64.decodebytes(image)
with open("image{}".format(c), 'wb') as f:
f.write(im)
c += 1
for l in range(128):
img = cv2.imread("image{}".format(l), cv2.IMREAD_ANYCOLOR);
# load the neural net. Should be local to this method as its multi-threaded endpoint
nets = load_model(CFG, Weights)
s = do_prediction(img, nets, Lables)
return jsonify(s)
except Exception as e:
print(e)
if __name__ == '__main__':
app.run(host='0.0.0.0', debug=True, threaded=True)
This creates the image files with different sizes but I cannot view them in image viewer. The files being recieved are jpg files. Ignoring that, I went ahead with the processing and I get
TypeError: The view function for 'main' did not return a valid response. The function either returned None or ended without a return statement.
Incorrect padding
Incorrect padding
[INFO] loading YOLO from disk...
'NoneType' object has no attribute 'shape'
Images are being sent like this.
python iWebLens_client.py inputfolder/ http://192.168.29.75:5000/api/object_detection 4
The images are being received like this.
b'"{\\"image\\": \\"/9j/4AAQSkZJRgABAQEASABIAAD/4gxYSUNDX1BST0ZJTEUAAQEAAAxITGlubwIQAABtbnRyUkdCIFhZWiAHzgACAAkABgAxAABhY3NwTVNGVAAAAABJRUMgc1JHQgAAAAAAAAAAAAAAAAAA......fiU05tQopHNf//Z\\", \\"id\\": \\"e3ad9809-b84c-57f1-bd03-a54e25c59bcc\\"}"'
I am thinking I need to decode('utf-8') this, but don't know how.
Currently, you are double-coding the data on the client side. Within requests, the argument passed is already converted to JSON.
Just pass the dict on as a json parameter.
def call_object_detection_service(image):
try:
url = str(sys.argv[2])
data = {}
#generate uuid for image
id = uuid.uuid5(uuid.NAMESPACE_OID, image)
# Encode image into base64 string
with open (image, 'rb') as image_file:
data['image'] = base64.b64encode(image_file.read()).decode('utf-8')
data['id'] = str(id)
headers = {'Content-Type': 'application/json'}
# HERE IS THE CHANGE !!!
response = requests.post(url, json=data, headers=headers)
if response.ok:
output = "Thread : {}, input image: {}, output:{}".format(
threading.current_thread().getName(),
image,
response.text
)
print(output)
else:
print ("Error, response status:{}".format(response))
except Exception as e:
print("Exception in webservice call: {}".format(e))
The data can now be received on the server as JSON and extracted into a dict.
#app.route('/api/object_detection', methods=['POST'])
def main():
data = request.get_json(force=True)
uid = data.get('id')
image = data.get('image')
# ... decode the base64 data here ...
return jsonify(message='done')

Python : Manga parsing return empty file

i want to parse images from a "certain" manga and chapter. here's my code:
import requests, bs4, os, urllib.request
try:
url = "http://manganelo.com/chapter/read_one_punch_man_manga_online_free3/chapter_136"
res = requests.get(url)
print("[+] Asking a request to " + url)
# slice the url so it only contains the name and chapter
name = url[34:].replace("/", "_")
os.mkdir(name)
print("[+] Making '{}' directory".format(name))
os.chdir(os.path.join(os.getcwd(), name))
soup = bs4.BeautifulSoup(res.text, "html.parser")
for img in soup.findAll("img"):
manga_url = img.get("src")
manga_name = img.get("alt") + ".jpg"
urllib.request.urlretrieve(manga_url, manga_name)
print("[+] Downloading: " + manga_name)
except Exception as e:
print("[-] Error: " + str(e))
it works fine BUT only for a specific chapter, let's say i put chapter 130, when i try to run the code it returns blank file but if i put chapter 136 or others it works fine. How can this happen?
you can replace urllib.request.urlretrieve(manga_url, manga_name)
with :
r = requests.get(manga_url, stream=True)
if r.status_code == 200:
with open(manga_name, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
Actually Remote server is apparently checking the user agent header and rejecting requests from Python's urllib.
On the other hand you can use :
opener = urllib.request.URLopener()
opener.addheader('User-Agent', 'whatever')
opener.retrieve(manga_url, manga_name)
This works for me
Hope this helps

python request urls parallel [duplicate]

This question already has an answer here:
How to send multiple http requests python
(1 answer)
Closed 6 years ago.
I created the following script to download images from an API endpoint which works as intended. Thing is that it is rather slow as all the requests have to wait on each other. What is the correct way to make it possible to still have the steps synchronously for each item I want to fetch, but make it parallel for each individual item. This from an online service called
servicem8
So what I hope to achieve is:
fetch all possible job ids => keep name/and other info
fetch name of the customer
fetch each attachment of a job
These three steps should be done for each job. So I could make things parallel for each job as they do not have to wait on each other.
Update:
Problem I do not understand is how can you make sure that you bundle for example the three calls per item in one call as its only per item that I can do things in parallel so for example when I want to
fetch item( fetch name => fetch description => fetch id)
so its the fetch item I want to make parallel?
The current code I have is working but rather slow:
import requests
import dateutil.parser
import shutil
import os
user = "test#test.com"
passw = "test"
print("Read json")
url = "https://api.servicem8.com/api_1.0/job.json"
r = requests.get(url, auth=(user, passw))
print("finished reading jobs.json file")
scheduled_jobs = []
if r.status_code == 200:
for item in r.json():
scheduled_date = item['job_is_scheduled_until_stamp']
try:
parsed_date = dateutil.parser.parse(scheduled_date)
if parsed_date.year == 2016:
if parsed_date.month == 10:
if parsed_date.day == 10:
url_customer = "https://api.servicem8.com/api_1.0/Company/{}.json".format(item[
'company_uuid'])
c = requests.get(url_customer, auth=(user, passw))
cus_name = c.json()['name']
scheduled_jobs.append(
[item['uuid'], item['generated_job_id'], cus_name])
except ValueError:
pass
for job in scheduled_jobs:
print("fetch for job {}".format(job))
url = "https://api.servicem8.com/api_1.0/Attachment.json?%24filter=related_object_uuid%20eq%20{}".format(job[
0])
r = requests.get(url, auth=(user, passw))
if r.json() == []:
pass
for attachment in r.json():
if attachment['active'] == 1 and attachment['file_type'] != '.pdf':
print("fetch for attachment {}".format(attachment))
url_staff = "https://api.servicem8.com/api_1.0/Staff.json?%24filter=uuid%20eq%20{}".format(
attachment['created_by_staff_uuid'])
s = requests.get(url_staff, auth=(user, passw))
for staff in s.json():
tech = "{}_{}".format(staff['first'], staff['last'])
url = "https://api.servicem8.com/api_1.0/Attachment/{}.file".format(attachment[
'uuid'])
r = requests.get(url, auth=(user, passw), stream=True)
if r.status_code == 200:
creation_date = dateutil.parser.parse(
attachment['timestamp']).strftime("%d.%m.%y")
if not os.path.exists(os.getcwd() + "/{}/{}".format(job[2], job[1])):
os.makedirs(os.getcwd() + "/{}/{}".format(job[2], job[1]))
path = os.getcwd() + "/{}/{}/SC -O {} {}{}".format(
job[2], job[1], creation_date, tech.upper(), attachment['file_type'])
print("writing file to path {}".format(path))
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
else:
print(r.text)
Update [14/10]
I updated the code in the following way with some hints given. Thanks a lot for that. Only thing I could optimize I guess is the attachment downloading but it is working fine now. Funny thing I learned is that you cannot create a CON folder on a windows machine :-) did not know that.
I use pandas as well just to try to avoid some loops in my list of dicts but not sure if I am already most performant. Longest is actually reading in the full json files. I fully read them in as I could not find an API way of just telling the api, return me only the jobs from september 2016. The api query function seems to work on eq/lt/ht.
import requests
import dateutil.parser
import shutil
import os
import pandas as pd
user = ""
passw = ""
FOLDER = os.getcwd()
headers = {"Accept-Encoding": "gzip, deflate"}
import grequests
urls = [
'https://api.servicem8.com/api_1.0/job.json',
'https://api.servicem8.com/api_1.0/Attachment.json',
'https://api.servicem8.com/api_1.0/Staff.json',
'https://api.servicem8.com/api_1.0/Company.json'
]
#Create a set of unsent Requests:
print("Read json files")
rs = (grequests.get(u, auth=(user, passw), headers=headers) for u in urls)
#Send them all at the same time:
jobs,attachments,staffs,companies = grequests.map(rs)
#create dataframes
df_jobs = pd.DataFrame(jobs.json())
df_attachments = pd.DataFrame(attachments.json())
df_staffs = pd.DataFrame(staffs.json())
df_companies = pd.DataFrame(companies.json())
#url_customer = "https://api.servicem8.com/api_1.0/Company/{}.json".format(item['company_uuid'])
#c = requests.get(url_customer, auth=(user, passw))
#url = "https://api.servicem8.com/api_1.0/job.json"
#jobs = requests.get(url, auth=(user, passw), headers=headers)
#print("Reading attachments json")
#url = "https://api.servicem8.com/api_1.0/Attachment.json"
#attachments = requests.get(url, auth=(user, passw), headers=headers)
#print("Reading staff.json")
#url_staff = "https://api.servicem8.com/api_1.0/Staff.json"
#staffs = requests.get(url_staff, auth=(user, passw))
scheduled_jobs = []
if jobs.status_code == 200:
print("finished reading json file")
for job in jobs.json():
scheduled_date = job['job_is_scheduled_until_stamp']
try:
parsed_date = dateutil.parser.parse(scheduled_date)
if parsed_date.year == 2016:
if parsed_date.month == 9:
cus_name = df_companies[df_companies.uuid == job['company_uuid']].iloc[0]['name'].upper()
cus_name = cus_name.replace('/', '')
scheduled_jobs.append([job['uuid'], job['generated_job_id'], cus_name])
except ValueError:
pass
print("{} jobs to fetch".format(len(scheduled_jobs)))
for job in scheduled_jobs:
print("fetch for job attachments {}".format(job))
#url = "https://api.servicem8.com/api_1.0/Attachment.json?%24filter=related_object_uuid%20eq%20{}".format(job[0])
if attachments == []:
pass
for attachment in attachments.json():
if attachment['related_object_uuid'] == job[0]:
if attachment['active'] == 1 and attachment['file_type'] != '.pdf' and attachment['attachment_source'] != 'INVOICE_SIGNOFF':
for staff in staffs.json():
if staff['uuid'] == attachment['created_by_staff_uuid']:
tech = "{}_{}".format(
staff['first'].split()[-1].strip(), staff['last'])
creation_timestamp = dateutil.parser.parse(
attachment['timestamp'])
creation_date = creation_timestamp.strftime("%d.%m.%y")
creation_time = creation_timestamp.strftime("%H_%M_%S")
path = FOLDER + "/{}/{}/SC_-O_D{}_T{}_{}{}".format(
job[2], job[1], creation_date, creation_time, tech.upper(), attachment['file_type'])
# fetch attachment
if not os.path.isfile(path):
url = "https://api.servicem8.com/api_1.0/Attachment/{}.file".format(attachment[
'uuid'])
r = requests.get(url, auth=(user, passw), stream = True)
if r.status_code == 200:
if not os.path.exists(FOLDER + "/{}/{}".format(job[2], job[1])):
os.makedirs(
FOLDER + "/{}/{}".format(job[2], job[1]))
print("writing file to path {}".format(path))
with open(path, 'wb') as f:
r.raw.decode_content = True
shutil.copyfileobj(r.raw, f)
else:
print("file already exists")
else:
print(r.text)
General idea is to use asynchronous url requests and there is a python module named grequests for that-https://github.com/kennethreitz/grequests
From Documentation:
import grequests
urls = [
'http://www.heroku.com',
'http://python-tablib.org',
'http://httpbin.org',
'http://python-requests.org',
'http://fakedomain/',
'http://kennethreitz.com'
]
#Create a set of unsent Requests:
rs = (grequests.get(u) for u in urls)
#Send them all at the same time:
grequests.map(rs)
And the resopnse
[<Response [200]>, <Response [200]>, <Response [200]>, <Response [200]>, None, <Response [200]>]

Extracting data from dictionary returned by json.loads

Here is what I am trying to do: Prompt for an URL, read the JSON data from that URL using urllib and then parse and extract the comment counts from the JSON data and compute their sum.
Here is what I have so far in Python:
import json
import urllib
serviceurl = 'http://python-data.dr-chuck.net/comments_42.json'
while True:
url = serviceurl + urllib.urlencode(('sensor':'false', 'address' : address))
print "Retrieving", url
uh = urllib.urlopen(url)
data = uh.read()
print "Retrieved", len(data), "characters"
try: js = json.loads(str(data))
except: js = None
print js.dumps(js, indent = 4)
js = ["comment"][0]["count"]
lst = list()
lst.append(js)
print sum(lst)
Here is what the JSON data looks like:
{
comments: [
{
name: "Matthias"
count: 97
},
{
name: "Geomer"
count: 97
}
...
]
}
I am using Python 2. This is my first time doing this, so any feedback you can give me about this would be helpful, especially after the try/except statements. Thanks in advance.
js is a dictionary looking like this:
{'comments': [{'count': 97, 'name': 'Matthias'}, {'count': 97, 'name': 'Geomer'}]}
You can get the sum of all 'count' values like this:
sum(nested_dict['count'] for nested_dict in js['comments'])
If there is a chance that one of the dictionaries in the list does not have a 'count' key, use dict.get with default value 0:
sum(nested_dict.get('count', 0) for nested_dict in js['comments'])
I've also done the same course and was on the same assignment. The answer by timgeb will get the job done in a smaller code. Alternatively, you can also try the following:
import json
import urllib
counts = list()
inp = raw_input('Enter a URL: ')
url = urllib.urlopen(inp)
data = url.read()
print len(data)
try:
js = json.loads(data)
except:
js = None
comments = js['comments']
for comment in comments:
counts.append(comment['count'])
print sum(counts)
#print sum(nested_dict['count'] for nested_dict in js['comments'])
you dont need to encode anything to the url, nor do you need a while loop. that segment of the code was used for using the google map API.
My version of code:
import json
import urllib.request, urllib.parse, urllib.error
total = 0
url = input('Enter URL: ')
data = urllib.request.urlopen(url).read().decode()
info = json.loads(data)
number = info["comments"] #getting list of all the dictinaries
for i in number: #in each dictionary...
needed = i.get('count') #... we are getting numbers from "count"
total = total + int(needed) #summ all the numbers
print(total)
Based on Mudit Sahni's code, but written for Python3
import urllib.request
import json
url = input("Enter URL: ")
response = urllib.request.urlopen(urllib.request.Request(url)).read().decode('utf-8')
data = json.loads(response)
counts = list()
comments = data['comments']
for comment in comments:
counts.append(comment['count'])
print (sum(counts))
import urllib.request, urllib.parse, urllib.error
import json
import ssl
# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
url = input('Enter - ')
print('Retrieving', url)
uh = urllib.request.urlopen(url, context=ctx)
data = uh.read()
info = json.loads(data)
#print(info) #to see the info dictionary/object
#print(json.dumps(info, indent=2))
count = 0
sum = 0
for item in info['comments']:
num = item['count']
sum = sum + int(num)
count = count + 1
print('Count: ', count)
print('Sum: ', sum)
## http://py4e-data.dr-chuck.net/comments_42.json total= 2553
## http://py4e-data.dr-chuck.net/comments_802780.json total= 2670
import ssl
import urllib.request, urllib.parse, urllib.error
import json
total= list()
## Ignore SSL certification
ctx= ssl.create_default_context
ctx.check_hostname= False
ctx.verify_mode= ssl.CERT_NONE
## Access url
url= input('Enter URL: ')
req= urllib.request.urlopen(url, context=ctx)
html= req.read().decode()
print('Retrieving URL:', url)
print('Retrieved', len(html),'characters')
##accessing data
js= json.loads(html)
#print(json.dumps(js, indent=3))
for counts in js["comments"]:
#print('Counts:', counts['count'])
total.append(counts['count'])
print(sum(total))
import urllib.request, urllib.parse, urllib.error
import ssl
import json
# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
while True:
count = sum = 0
url = input('Enter location: ')
if len(url) < 1: break
print('Retrieving', url)
uh = urllib.request.urlopen(url, context=ctx)
data = uh.read()
print('Retrieved', len(data), 'characters')
info = json.loads(data)
for item in info['comments']:
count+=1
sum+=int(item['count'])
print('count:',count)
print('sum',sum)
from urllib.request import urlopen
import json
while True:
url = input('Enter url: ')
if len(url) < 1:
break
print("Retrieving", url)
uh = urlopen(url)
data = uh.read().decode()
print("Retrieved", len(data), "characters")
try:
js = json.loads(data)
except:
js = None
count = 0
lst = list()
for comment in js["comments"]:
count += 1
lst.append(comment["count"])
print("count:", count)
print(sum(lst))
import urllib.request, urllib.parse, urllib.error
import json
url = "http://py4e-data.dr-chuck.net/comments_1418532.json"
info = json.loads(urllib.request.urlopen(url).read())
comm=info['comments']
counts_list = [int(items['count']) for items in comm]
print(sum(counts_list))
import json
import urllib
url=raw_input('Enter location:')
print 'Retrieving',url
uh=urllib.urlopen(url)
data=uh.read()
info = json.loads(data)
print 'Retrieved', len(info)
sum=0
counts=0
for item in info['comments']:
sum=sum+item['count']
counts=counts+1
print 'Counts:',counts
print 'Sum:',sum
import urllib.request, urllib.parse, urllib.error
import ssl
import json
#to ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
url = input('Enter - ')
data = urllib.request.urlopen(url, context=ctx).read()
info = json.loads(data)
sum_count = 0
for a in info["comments"]:
sum_count += int(a["count"])
print(sum)

Categories

Resources