Download image over https using python

download_image.py

# using socket
import socket
import time

HOST = 'data.pr4e.org'
PORT = 80
mysock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
mysock.connect((HOST, PORT))
mysock.sendall(b'GET http://data.pr4e.org/cover3.jpg HTTP/1.0\r\n\r\n')
count = 0
picture = b''

while True:
    data = mysock.recv(5120)  # receive data in groups of 5120 characters
    if len(data) < 1: break
    time.sleep(0.25)  # allows server to be "ahead" of us by 0.25s
    count += len(data)
    print(len(data), count)
    # if we uncomment time.sleep(0.25), we are more likely to get < 5210 bytes sometimes
    picture = picture + data

mysock.close()  # close socket

# Look for the end of the header file
pos = picture.find(b'\r\n\r\n')  # end indicated by 2 * (endline + newline)
print('Header length ', pos)
print(picture[:pos].decode())  # pos marks the end

# Skip past the header and save the picture data
picture = picture[pos + 4:]
fhand = open('stuff.jpg', 'wb')
fhand.write(picture)
fhand.close()  # must ensure that file is permanently saved

download_image_urllib.py

# using urllib, which simplifies the code
import urllib.request, urllib.parse, urllib.error

img = urllib.request.urlopen('http://data.pr4e.org/cover3.jpg') # img is a string variable
fhand = open('cover3.jpg', 'wb')
size = 0

while True:
    info = img.read(100000) # reads 100,000 characters at a time, prevents crash
    if len(info) < 1: break
    size += len(info)
    fhand.write(info)   # for small files, we can simply go with fhand.write(img)

print(size, ' characters copied')   # 230210 characters copied
fhand.close()