How to efficiently read and save video from an IP camera?

Question 1

*edit I previously blamed GIL for the behavior which was silly. This is an I/O bound process, not a CPU-bound process. So multiprocessing is not a meaningful solution.

*update I finally found a demo ip camera with the same streaming interface as yours (I think). Using the streaming interface, it only makes a connection once and then reads from the stream of data as if it were a file to extract jpg image frames. With the code below, I grabbed for 2 seconds ==> 27 frames which I believe extrapolates to about 300k images in a 7 hour period.

If you want to get even more, you would move the image modification and file writing to a separate thread and have a worker doing that while the main thread just grabs from the stream and sends jpeg data to the worker.

import base64
from datetime import datetime
import httplib
import io
import os
import time

from PIL import ImageFont
from PIL import Image
from PIL import ImageDraw


wdir = "workdir"
stream_url = ''
username = ''
password = ''


def main():
    time_count = 2
    looper_stream(time_count)


def looper_stream(time_count):
    h = httplib.HTTP(stream_url)
    h.putrequest('GET', '/videostream.cgi')
    h.putheader('Authorization', 'Basic %s' % base64.encodestring('%s:%s' % (username, password))[:-1])
    h.endheaders()
    errcode, errmsg, headers = h.getreply()
    stream_file = h.getfile()
    start = time.time()
    end = start + time_count
    while time.time() <= end:
        now = datetime.now()
        dte = str(now.day) + "-" + str(now.month) + "-" + str(now.year)
        dte1 = str(now.hour) + "-" + str(now.minute) + "-" + str(now.second) + "." + str(now.microsecond)
        cname = "Cam1-"
        dnow = """Date: %s """ % dte
        dnow1 = """Time: %s""" % dte1
        # your camera may have a different streaming format
        # but I think you can figure it out from the debug style below
        source_name = stream_file.readline()    # '--ipcamera'
        content_type = stream_file.readline()    # 'Content-Type: image/jpeg'
        content_length = stream_file.readline()   # 'Content-Length: 19565'
        print 'confirm/adjust content (source?): ' + source_name
        print 'confirm/adjust content (type?): ' + content_type
        print 'confirm/adjust content (length?): ' + content_length
        # find the beginning of the jpeg data BEFORE pulling the jpeg framesize
        # there must be a more efficient way, but hopefully this is not too bad
        b1 = b2 = b''
        while True:
            b1 = stream_file.read(1)
            while b1 != chr(0xff):
                b1 = stream_file.read(1)
            b2 = stream_file.read(1)
            if b2 == chr(0xd8):
                break
        # pull the jpeg data
        framesize = int(content_length[16:])
        jpeg_stripped = b''.join((b1, b2, stream_file.read(framesize - 2)))
        # throw away the remaining stream data. Sorry I have no idea what it is
        junk_for_now = stream_file.readline()
        # convert directly to an Image instead of saving / reopening
        # thanks to SO: http://stackoverflow.com/a/12020860/377366
        image_as_file = io.BytesIO(jpeg_stripped)
        image_as_pil = Image.open(image_as_file)
        draw = ImageDraw.Draw(image_as_pil)
        draw.text((0, 0), cname, fill="white")
        draw.text((0, 10), dnow, fill="white")
        draw.text((0, 20), dnow1, fill="white")
        img_name = "Cam1-" + dte + dte1 + ".jpg"
        img_path = os.path.join(wdir, img_name)
        image_as_pil.save(img_path)


if __name__ == '__main__':
    main()

*jpg capture below doesn't seem fast enough which is logical. making so many http requests would be slow for anything.

from datetime import datetime
import io
import threading
import os
import time

import urllib2

from PIL import ImageFont
from PIL import Image
from PIL import ImageDraw


wdir = "workdir"


def looper(time_count, loop_name):
    start = time.time()
    end = start + time_count
    font = ImageFont.truetype("/usr/share/fonts/truetype/ttf-dejavu/DejaVuSans.ttf", 10)
    while time.time() <= end:
        now = datetime.now()
        dte = str(now.day) + "-" + str(now.month) + "-" + str(now.year)
        dte1 = str(now.hour) + "-" + str(now.minute) + "-" + str(now.second) + "." + str(now.microsecond)
        cname = "Cam1-"
        dnow = """Date: %s """ % dte
        dnow1 = """Time: %s""" % dte1
        image = urllib2.urlopen('http://(ip address)/snapshot.cgi?user=uname&pwd=password').read()
        # convert directly to an Image instead of saving / reopening
        # thanks to SO: http://stackoverflow.com/a/12020860/377366
        image_as_file = io.BytesIO(image)
        image_as_pil = Image.open(image_as_file)
        draw = ImageDraw.Draw(image_as_pil)
        draw_text = "\n".join((cname, dnow, dnow1))
        draw.text((0, 0), draw_text, fill="white", font=font)
        #draw.text((0, 0), cname, fill="white", font=font)
        #draw.text((0, 10), dnow, fill="white", font=font)
        #draw.text((0, 20), dnow1, fill="white", font=font)
        img_name = "Cam1-" + dte + dte1 + "(" + loop_name + ").jpg"
        img_path = os.path.join(wdir, img_name)
        image_as_pil.save(img_path)


if __name__ == '__main__':
    time_count = 5
    threads = list()
    for i in range(2):
        name = str(i)
        t = threading.Thread(target=looper, args=(time_count, name))
        threads.append(p)
        t.start()
    for t in threads:
        t.join()

Question 2

The speeds you are getting for the implementation you have given are not bad.

You are writing about 4.5 frames per second (fps), and zoneminder is writing out nearly 10 fps. Below is your flow diagram with a few comments to speed things up

You are reading the url buffer (network latency),
then writing the image (disk latency 1) (you might not need to write the image here to disk - consider passing it directly to your img class)
reading the image (disk latency 2)
then manipulating the image using fonts, text boxes etc... (3 image draws) - Can you build one string with newlines so that you only make one call to the draw.text function?
writing the output image (disk latency 3)

Question 3

There are a couple of things that might help.

Lift the font-opening from the function to the main code, then pass in the font object (opening a font is likely to be non-trivial in time, by doing it once, you're not taking the time hit for every image; you never modify the font on the fly, so sharing the same font object should be OK).
You can probably scrap two of the three lines that contain:

draw = ImageDraw.Draw(img)