renumbering chapters >= 19
This commit is contained in:
31
20-futures/demo_executor_map.py
Normal file
31
20-futures/demo_executor_map.py
Normal file
@@ -0,0 +1,31 @@
|
||||
"""
|
||||
Experiment with ``ThreadPoolExecutor.map``
|
||||
"""
|
||||
# tag::EXECUTOR_MAP[]
|
||||
from time import sleep, strftime
|
||||
from concurrent import futures
|
||||
|
||||
def display(*args): # <1>
|
||||
print(strftime('[%H:%M:%S]'), end=' ')
|
||||
print(*args)
|
||||
|
||||
def loiter(n): # <2>
|
||||
msg = '{}loiter({}): doing nothing for {}s...'
|
||||
display(msg.format('\t'*n, n, n))
|
||||
sleep(n)
|
||||
msg = '{}loiter({}): done.'
|
||||
display(msg.format('\t'*n, n))
|
||||
return n * 10 # <3>
|
||||
|
||||
def main():
|
||||
display('Script starting.')
|
||||
executor = futures.ThreadPoolExecutor(max_workers=3) # <4>
|
||||
results = executor.map(loiter, range(5)) # <5>
|
||||
display('results:', results) # <6>
|
||||
display('Waiting for individual results:')
|
||||
for i, result in enumerate(results): # <7>
|
||||
display(f'result {i}: {result}')
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
# end::EXECUTOR_MAP[]
|
||||
1
20-futures/getflags/.gitignore
vendored
Normal file
1
20-futures/getflags/.gitignore
vendored
Normal file
@@ -0,0 +1 @@
|
||||
flags/
|
||||
8
20-futures/getflags/country_codes.txt
Normal file
8
20-futures/getflags/country_codes.txt
Normal file
@@ -0,0 +1,8 @@
|
||||
AD AE AF AG AL AM AO AR AT AU AZ BA BB BD BE BF BG BH BI BJ BN BO BR BS BT
|
||||
BW BY BZ CA CD CF CG CH CI CL CM CN CO CR CU CV CY CZ DE DJ DK DM DZ EC EE
|
||||
EG ER ES ET FI FJ FM FR GA GB GD GE GH GM GN GQ GR GT GW GY HN HR HT HU ID
|
||||
IE IL IN IQ IR IS IT JM JO JP KE KG KH KI KM KN KP KR KW KZ LA LB LC LI LK
|
||||
LR LS LT LU LV LY MA MC MD ME MG MH MK ML MM MN MR MT MU MV MW MX MY MZ NA
|
||||
NE NG NI NL NO NP NR NZ OM PA PE PG PH PK PL PT PW PY QA RO RS RU RW SA SB
|
||||
SC SD SE SG SI SK SL SM SN SO SR SS ST SV SY SZ TD TG TH TJ TL TM TN TO TR
|
||||
TT TV TW TZ UA UG US UY UZ VA VC VE VN VU WS YE ZA ZM ZW
|
||||
1
20-futures/getflags/downloaded/.gitignore
vendored
Normal file
1
20-futures/getflags/downloaded/.gitignore
vendored
Normal file
@@ -0,0 +1 @@
|
||||
*.gif
|
||||
55
20-futures/getflags/flags.py
Executable file
55
20-futures/getflags/flags.py
Executable file
@@ -0,0 +1,55 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of top 20 countries by population
|
||||
|
||||
Sequential version
|
||||
|
||||
Sample runs (first with new domain, so no caching ever)::
|
||||
|
||||
$ ./flags.py
|
||||
BD BR CD CN DE EG ET FR ID IN IR JP MX NG PH PK RU TR US VN
|
||||
20 downloads in 26.21s
|
||||
$ ./flags.py
|
||||
BD BR CD CN DE EG ET FR ID IN IR JP MX NG PH PK RU TR US VN
|
||||
20 downloads in 14.57s
|
||||
|
||||
|
||||
"""
|
||||
|
||||
# tag::FLAGS_PY[]
|
||||
import time
|
||||
from pathlib import Path
|
||||
from typing import Callable
|
||||
|
||||
import requests # <1>
|
||||
|
||||
POP20_CC = ('CN IN US ID BR PK NG BD RU JP '
|
||||
'MX PH VN ET EG DE IR TR CD FR').split() # <2>
|
||||
|
||||
BASE_URL = 'http://fluentpython.com/data/flags' # <3>
|
||||
DEST_DIR = Path('downloaded') # <4>
|
||||
|
||||
def save_flag(img: bytes, filename: str) -> None: # <5>
|
||||
(DEST_DIR / filename).write_bytes(img)
|
||||
|
||||
def get_flag(cc: str) -> bytes: # <6>
|
||||
url = f'{BASE_URL}/{cc}/{cc}.gif'.lower()
|
||||
resp = requests.get(url)
|
||||
return resp.content
|
||||
|
||||
def download_many(cc_list: list[str]) -> int: # <7>
|
||||
for cc in sorted(cc_list): # <8>
|
||||
image = get_flag(cc)
|
||||
save_flag(image, f'{cc}.gif')
|
||||
print(cc, end=' ', flush=True) # <9>
|
||||
return len(cc_list)
|
||||
|
||||
def main(downloader: Callable[[list[str]], int]) -> None: # <10>
|
||||
t0 = time.perf_counter() # <11>
|
||||
count = downloader(POP20_CC)
|
||||
elapsed = time.perf_counter() - t0
|
||||
print(f'\n{count} downloads in {elapsed:.2f}s')
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many) # <12>
|
||||
# end::FLAGS_PY[]
|
||||
BIN
20-futures/getflags/flags.zip
Normal file
BIN
20-futures/getflags/flags.zip
Normal file
Binary file not shown.
103
20-futures/getflags/flags2_asyncio.py
Executable file
103
20-futures/getflags/flags2_asyncio.py
Executable file
@@ -0,0 +1,103 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of countries (with error handling).
|
||||
|
||||
asyncio async/await version
|
||||
|
||||
"""
|
||||
# tag::FLAGS2_ASYNCIO_TOP[]
|
||||
import asyncio
|
||||
from collections import Counter
|
||||
|
||||
import aiohttp
|
||||
import tqdm # type: ignore
|
||||
|
||||
from flags2_common import main, HTTPStatus, Result, save_flag
|
||||
|
||||
# default set low to avoid errors from remote site, such as
|
||||
# 503 - Service Temporarily Unavailable
|
||||
DEFAULT_CONCUR_REQ = 5
|
||||
MAX_CONCUR_REQ = 1000
|
||||
|
||||
|
||||
class FetchError(Exception): # <1>
|
||||
def __init__(self, country_code: str):
|
||||
self.country_code = country_code
|
||||
|
||||
|
||||
async def get_flag(session: aiohttp.ClientSession, # <2>
|
||||
base_url: str,
|
||||
cc: str) -> bytes:
|
||||
url = f'{base_url}/{cc}/{cc}.gif'.lower()
|
||||
async with session.get(url) as resp:
|
||||
if resp.status == 200:
|
||||
return await resp.read()
|
||||
else:
|
||||
resp.raise_for_status() # <3>
|
||||
return bytes()
|
||||
|
||||
async def download_one(session: aiohttp.ClientSession, # <4>
|
||||
cc: str,
|
||||
base_url: str,
|
||||
semaphore: asyncio.Semaphore,
|
||||
verbose: bool) -> Result:
|
||||
try:
|
||||
async with semaphore: # <5>
|
||||
image = await get_flag(session, base_url, cc)
|
||||
except aiohttp.ClientResponseError as exc:
|
||||
if exc.status == 404: # <6>
|
||||
status = HTTPStatus.not_found
|
||||
msg = 'not found'
|
||||
else:
|
||||
raise FetchError(cc) from exc # <7>
|
||||
else:
|
||||
save_flag(image, f'{cc}.gif')
|
||||
status = HTTPStatus.ok
|
||||
msg = 'OK'
|
||||
if verbose and msg:
|
||||
print(cc, msg)
|
||||
return Result(status, cc)
|
||||
# end::FLAGS2_ASYNCIO_TOP[]
|
||||
|
||||
# tag::FLAGS2_ASYNCIO_START[]
|
||||
async def supervisor(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
concur_req: int) -> Counter[HTTPStatus]: # <1>
|
||||
counter: Counter[HTTPStatus] = Counter()
|
||||
semaphore = asyncio.Semaphore(concur_req) # <2>
|
||||
async with aiohttp.ClientSession() as session:
|
||||
to_do = [download_one(session, cc, base_url, semaphore, verbose)
|
||||
for cc in sorted(cc_list)] # <3>
|
||||
to_do_iter = asyncio.as_completed(to_do) # <4>
|
||||
if not verbose:
|
||||
to_do_iter = tqdm.tqdm(to_do_iter, total=len(cc_list)) # <5>
|
||||
for coro in to_do_iter: # <6>
|
||||
try:
|
||||
res = await coro # <7>
|
||||
except FetchError as exc: # <8>
|
||||
country_code = exc.country_code # <9>
|
||||
try:
|
||||
error_msg = exc.__cause__.message # type: ignore # <10>
|
||||
except AttributeError:
|
||||
error_msg = 'Unknown cause' # <11>
|
||||
if verbose and error_msg:
|
||||
print(f'*** Error for {country_code}: {error_msg}')
|
||||
status = HTTPStatus.error
|
||||
else:
|
||||
status = res.status
|
||||
counter[status] += 1 # <12>
|
||||
return counter # <13>
|
||||
|
||||
def download_many(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
concur_req: int) -> Counter[HTTPStatus]:
|
||||
coro = supervisor(cc_list, base_url, verbose, concur_req)
|
||||
counts = asyncio.run(coro) # <14>
|
||||
|
||||
return counts
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many, DEFAULT_CONCUR_REQ, MAX_CONCUR_REQ)
|
||||
# end::FLAGS2_ASYNCIO_START[]
|
||||
109
20-futures/getflags/flags2_asyncio_executor.py
Executable file
109
20-futures/getflags/flags2_asyncio_executor.py
Executable file
@@ -0,0 +1,109 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of countries (with error handling).
|
||||
|
||||
asyncio async/await version using run_in_executor for save_flag.
|
||||
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from collections import Counter
|
||||
|
||||
import aiohttp
|
||||
import tqdm # type: ignore
|
||||
|
||||
from flags2_common import main, HTTPStatus, Result, save_flag
|
||||
|
||||
# default set low to avoid errors from remote site, such as
|
||||
# 503 - Service Temporarily Unavailable
|
||||
DEFAULT_CONCUR_REQ = 5
|
||||
MAX_CONCUR_REQ = 1000
|
||||
|
||||
|
||||
class FetchError(Exception):
|
||||
def __init__(self, country_code: str):
|
||||
self.country_code = country_code
|
||||
|
||||
|
||||
async def get_flag(session: aiohttp.ClientSession,
|
||||
base_url: str,
|
||||
cc: str) -> bytes:
|
||||
url = f'{base_url}/{cc}/{cc}.gif'.lower()
|
||||
async with session.get(url) as resp:
|
||||
if resp.status == 200:
|
||||
return await resp.read()
|
||||
else:
|
||||
resp.raise_for_status()
|
||||
return bytes()
|
||||
|
||||
# tag::FLAGS2_ASYNCIO_EXECUTOR[]
|
||||
async def download_one(session: aiohttp.ClientSession,
|
||||
cc: str,
|
||||
base_url: str,
|
||||
semaphore: asyncio.Semaphore,
|
||||
verbose: bool) -> Result:
|
||||
try:
|
||||
async with semaphore:
|
||||
image = await get_flag(session, base_url, cc)
|
||||
except aiohttp.ClientResponseError as exc:
|
||||
if exc.status == 404:
|
||||
status = HTTPStatus.not_found
|
||||
msg = 'not found'
|
||||
else:
|
||||
raise FetchError(cc) from exc
|
||||
else:
|
||||
loop = asyncio.get_running_loop() # <1>
|
||||
loop.run_in_executor(None, # <2>
|
||||
save_flag, image, f'{cc}.gif') # <3>
|
||||
status = HTTPStatus.ok
|
||||
msg = 'OK'
|
||||
if verbose and msg:
|
||||
print(cc, msg)
|
||||
return Result(status, cc)
|
||||
# end::FLAGS2_ASYNCIO_EXECUTOR[]
|
||||
|
||||
async def supervisor(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
concur_req: int) -> Counter[HTTPStatus]:
|
||||
counter: Counter[HTTPStatus] = Counter()
|
||||
semaphore = asyncio.Semaphore(concur_req)
|
||||
async with aiohttp.ClientSession() as session:
|
||||
to_do = [download_one(session, cc, base_url, semaphore, verbose)
|
||||
for cc in sorted(cc_list)]
|
||||
|
||||
to_do_iter = asyncio.as_completed(to_do)
|
||||
if not verbose:
|
||||
to_do_iter = tqdm.tqdm(to_do_iter, total=len(cc_list))
|
||||
for coro in to_do_iter:
|
||||
try:
|
||||
res = await coro
|
||||
except FetchError as exc:
|
||||
country_code = exc.country_code
|
||||
try:
|
||||
error_msg = exc.__cause__.message # type: ignore
|
||||
except AttributeError:
|
||||
error_msg = 'Unknown cause'
|
||||
if verbose and error_msg:
|
||||
print(f'*** Error for {country_code}: {error_msg}')
|
||||
status = HTTPStatus.error
|
||||
else:
|
||||
status = res.status
|
||||
|
||||
counter[status] += 1
|
||||
|
||||
return counter
|
||||
|
||||
|
||||
def download_many(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
concur_req: int) -> Counter[HTTPStatus]:
|
||||
coro = supervisor(cc_list, base_url, verbose, concur_req)
|
||||
counts = asyncio.run(coro) # <14>
|
||||
|
||||
return counts
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many, DEFAULT_CONCUR_REQ, MAX_CONCUR_REQ)
|
||||
159
20-futures/getflags/flags2_common.py
Normal file
159
20-futures/getflags/flags2_common.py
Normal file
@@ -0,0 +1,159 @@
|
||||
"""Utilities for second set of flag examples.
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import string
|
||||
import sys
|
||||
import time
|
||||
from collections import namedtuple, Counter
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
|
||||
Result = namedtuple('Result', 'status data')
|
||||
|
||||
HTTPStatus = Enum('HTTPStatus', 'ok not_found error')
|
||||
|
||||
POP20_CC = ('CN IN US ID BR PK NG BD RU JP '
|
||||
'MX PH VN ET EG DE IR TR CD FR').split()
|
||||
|
||||
DEFAULT_CONCUR_REQ = 1
|
||||
MAX_CONCUR_REQ = 1
|
||||
|
||||
SERVERS = {
|
||||
'REMOTE': 'http://fluentpython.com/data/flags',
|
||||
'LOCAL': 'http://localhost:8000/flags',
|
||||
'DELAY': 'http://localhost:8001/flags',
|
||||
'ERROR': 'http://localhost:8002/flags',
|
||||
}
|
||||
DEFAULT_SERVER = 'LOCAL'
|
||||
|
||||
DEST_DIR = Path('downloaded')
|
||||
COUNTRY_CODES_FILE = Path('country_codes.txt')
|
||||
|
||||
|
||||
def save_flag(img: bytes, filename: str) -> None:
|
||||
(DEST_DIR / filename).write_bytes(img)
|
||||
|
||||
|
||||
def initial_report(cc_list: list[str],
|
||||
actual_req: int,
|
||||
server_label: str) -> None:
|
||||
if len(cc_list) <= 10:
|
||||
cc_msg = ', '.join(cc_list)
|
||||
else:
|
||||
cc_msg = f'from {cc_list[0]} to {cc_list[-1]}'
|
||||
print(f'{server_label} site: {SERVERS[server_label]}')
|
||||
plural = 's' if len(cc_list) != 1 else ''
|
||||
print(f'Searching for {len(cc_list)} flag{plural}: {cc_msg}')
|
||||
if actual_req == 1:
|
||||
print('1 connection will be used.')
|
||||
else:
|
||||
print(f'{actual_req} concurrent connections will be used.')
|
||||
|
||||
|
||||
def final_report(cc_list: list[str],
|
||||
counter: Counter[HTTPStatus],
|
||||
start_time: float) -> None:
|
||||
elapsed = time.perf_counter() - start_time
|
||||
print('-' * 20)
|
||||
plural = 's' if counter[HTTPStatus.ok] != 1 else ''
|
||||
print(f'{counter[HTTPStatus.ok]} flag{plural} downloaded.')
|
||||
if counter[HTTPStatus.not_found]:
|
||||
print(f'{counter[HTTPStatus.not_found]} not found.')
|
||||
if counter[HTTPStatus.error]:
|
||||
plural = 's' if counter[HTTPStatus.error] != 1 else ''
|
||||
print(f'{counter[HTTPStatus.error]} error{plural}.')
|
||||
print(f'Elapsed time: {elapsed:.2f}s')
|
||||
|
||||
|
||||
def expand_cc_args(every_cc: bool,
|
||||
all_cc: bool,
|
||||
cc_args: list[str],
|
||||
limit: int) -> list[str]:
|
||||
codes: set[str] = set()
|
||||
A_Z = string.ascii_uppercase
|
||||
if every_cc:
|
||||
codes.update(a+b for a in A_Z for b in A_Z)
|
||||
elif all_cc:
|
||||
text = COUNTRY_CODES_FILE.read_text()
|
||||
codes.update(text.split())
|
||||
else:
|
||||
for cc in (c.upper() for c in cc_args):
|
||||
if len(cc) == 1 and cc in A_Z:
|
||||
codes.update(cc + c for c in A_Z)
|
||||
elif len(cc) == 2 and all(c in A_Z for c in cc):
|
||||
codes.add(cc)
|
||||
else:
|
||||
raise ValueError('*** Usage error: each CC argument '
|
||||
'must be A to Z or AA to ZZ.')
|
||||
return sorted(codes)[:limit]
|
||||
|
||||
|
||||
def process_args(default_concur_req):
|
||||
server_options = ', '.join(sorted(SERVERS))
|
||||
parser = argparse.ArgumentParser(
|
||||
description='Download flags for country codes. '
|
||||
'Default: top 20 countries by population.')
|
||||
parser.add_argument(
|
||||
'cc', metavar='CC', nargs='*',
|
||||
help='country code or 1st letter (eg. B for BA...BZ)')
|
||||
parser.add_argument(
|
||||
'-a', '--all', action='store_true',
|
||||
help='get all available flags (AD to ZW)')
|
||||
parser.add_argument(
|
||||
'-e', '--every', action='store_true',
|
||||
help='get flags for every possible code (AA...ZZ)')
|
||||
parser.add_argument(
|
||||
'-l', '--limit', metavar='N', type=int, help='limit to N first codes',
|
||||
default=sys.maxsize)
|
||||
parser.add_argument(
|
||||
'-m', '--max_req', metavar='CONCURRENT', type=int,
|
||||
default=default_concur_req,
|
||||
help=f'maximum concurrent requests (default={default_concur_req})')
|
||||
parser.add_argument(
|
||||
'-s', '--server', metavar='LABEL', default=DEFAULT_SERVER,
|
||||
help=f'Server to hit; one of {server_options} '
|
||||
f'(default={DEFAULT_SERVER})')
|
||||
parser.add_argument(
|
||||
'-v', '--verbose', action='store_true',
|
||||
help='output detailed progress info')
|
||||
args = parser.parse_args()
|
||||
if args.max_req < 1:
|
||||
print('*** Usage error: --max_req CONCURRENT must be >= 1')
|
||||
parser.print_usage()
|
||||
# "standard" exit status codes:
|
||||
# https://stackoverflow.com/questions/1101957/are-there-any-standard-exit-status-codes-in-linux/40484670#40484670
|
||||
sys.exit(2) # command line usage error
|
||||
if args.limit < 1:
|
||||
print('*** Usage error: --limit N must be >= 1')
|
||||
parser.print_usage()
|
||||
sys.exit(2) # command line usage error
|
||||
args.server = args.server.upper()
|
||||
if args.server not in SERVERS:
|
||||
print(f'*** Usage error: --server LABEL '
|
||||
f'must be one of {server_options}')
|
||||
parser.print_usage()
|
||||
sys.exit(2) # command line usage error
|
||||
try:
|
||||
cc_list = expand_cc_args(args.every, args.all, args.cc, args.limit)
|
||||
except ValueError as exc:
|
||||
print(exc.args[0])
|
||||
parser.print_usage()
|
||||
sys.exit(2) # command line usage error
|
||||
|
||||
if not cc_list:
|
||||
cc_list = sorted(POP20_CC)
|
||||
return args, cc_list
|
||||
|
||||
|
||||
def main(download_many, default_concur_req, max_concur_req):
|
||||
args, cc_list = process_args(default_concur_req)
|
||||
actual_req = min(args.max_req, max_concur_req, len(cc_list))
|
||||
initial_report(cc_list, actual_req, args.server)
|
||||
base_url = SERVERS[args.server]
|
||||
t0 = time.perf_counter()
|
||||
counter = download_many(cc_list, base_url, args.verbose, actual_req)
|
||||
assert sum(counter.values()) == len(cc_list), (
|
||||
'some downloads are unaccounted for'
|
||||
)
|
||||
final_report(cc_list, counter, t0)
|
||||
90
20-futures/getflags/flags2_sequential.py
Executable file
90
20-futures/getflags/flags2_sequential.py
Executable file
@@ -0,0 +1,90 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of countries (with error handling).
|
||||
|
||||
Sequential version
|
||||
|
||||
Sample run::
|
||||
|
||||
$ python3 flags2_sequential.py -s DELAY b
|
||||
DELAY site: http://localhost:8002/flags
|
||||
Searching for 26 flags: from BA to BZ
|
||||
1 concurrent connection will be used.
|
||||
--------------------
|
||||
17 flags downloaded.
|
||||
9 not found.
|
||||
Elapsed time: 13.36s
|
||||
|
||||
"""
|
||||
|
||||
from collections import Counter
|
||||
|
||||
import requests
|
||||
import tqdm # type: ignore
|
||||
|
||||
from flags2_common import main, save_flag, HTTPStatus, Result
|
||||
|
||||
DEFAULT_CONCUR_REQ = 1
|
||||
MAX_CONCUR_REQ = 1
|
||||
|
||||
# tag::FLAGS2_BASIC_HTTP_FUNCTIONS[]
|
||||
def get_flag(base_url: str, cc: str) -> bytes:
|
||||
url = f'{base_url}/{cc}/{cc}.gif'.lower()
|
||||
resp = requests.get(url)
|
||||
if resp.status_code != 200: # <1>
|
||||
resp.raise_for_status()
|
||||
return resp.content
|
||||
|
||||
def download_one(cc: str, base_url: str, verbose: bool = False):
|
||||
try:
|
||||
image = get_flag(base_url, cc)
|
||||
except requests.exceptions.HTTPError as exc: # <2>
|
||||
res = exc.response
|
||||
if res.status_code == 404:
|
||||
status = HTTPStatus.not_found # <3>
|
||||
msg = 'not found'
|
||||
else: # <4>
|
||||
raise
|
||||
else:
|
||||
save_flag(image, f'{cc}.gif')
|
||||
status = HTTPStatus.ok
|
||||
msg = 'OK'
|
||||
|
||||
if verbose: # <5>
|
||||
print(cc, msg)
|
||||
|
||||
return Result(status, cc) # <6>
|
||||
# end::FLAGS2_BASIC_HTTP_FUNCTIONS[]
|
||||
|
||||
# tag::FLAGS2_DOWNLOAD_MANY_SEQUENTIAL[]
|
||||
def download_many(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
_unused_concur_req: int) -> Counter[int]:
|
||||
counter: Counter[int] = Counter() # <1>
|
||||
cc_iter = sorted(cc_list) # <2>
|
||||
if not verbose:
|
||||
cc_iter = tqdm.tqdm(cc_iter) # <3>
|
||||
for cc in cc_iter: # <4>
|
||||
try:
|
||||
res = download_one(cc, base_url, verbose) # <5>
|
||||
except requests.exceptions.HTTPError as exc: # <6>
|
||||
error_msg = 'HTTP error {res.status_code} - {res.reason}'
|
||||
error_msg = error_msg.format(res=exc.response)
|
||||
except requests.exceptions.ConnectionError: # <7>
|
||||
error_msg = 'Connection error'
|
||||
else: # <8>
|
||||
error_msg = ''
|
||||
status = res.status
|
||||
|
||||
if error_msg:
|
||||
status = HTTPStatus.error # <9>
|
||||
counter[status] += 1 # <10>
|
||||
if verbose and error_msg: # <11>
|
||||
print(f'*** Error for {cc}: {error_msg}')
|
||||
|
||||
return counter # <12>
|
||||
# end::FLAGS2_DOWNLOAD_MANY_SEQUENTIAL[]
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many, DEFAULT_CONCUR_REQ, MAX_CONCUR_REQ)
|
||||
73
20-futures/getflags/flags2_threadpool.py
Executable file
73
20-futures/getflags/flags2_threadpool.py
Executable file
@@ -0,0 +1,73 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of countries (with error handling).
|
||||
|
||||
ThreadPool version
|
||||
|
||||
Sample run::
|
||||
|
||||
$ python3 flags2_threadpool.py -s ERROR -e
|
||||
ERROR site: http://localhost:8003/flags
|
||||
Searching for 676 flags: from AA to ZZ
|
||||
30 concurrent connections will be used.
|
||||
--------------------
|
||||
150 flags downloaded.
|
||||
361 not found.
|
||||
165 errors.
|
||||
Elapsed time: 7.46s
|
||||
|
||||
"""
|
||||
|
||||
# tag::FLAGS2_THREADPOOL[]
|
||||
from collections import Counter
|
||||
from concurrent import futures
|
||||
|
||||
import requests
|
||||
import tqdm # type: ignore # <1>
|
||||
|
||||
from flags2_common import main, HTTPStatus # <2>
|
||||
from flags2_sequential import download_one # <3>
|
||||
|
||||
DEFAULT_CONCUR_REQ = 30 # <4>
|
||||
MAX_CONCUR_REQ = 1000 # <5>
|
||||
|
||||
|
||||
def download_many(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
concur_req: int) -> Counter[int]:
|
||||
counter: Counter[int] = Counter()
|
||||
with futures.ThreadPoolExecutor(max_workers=concur_req) as executor: # <6>
|
||||
to_do_map = {} # <7>
|
||||
for cc in sorted(cc_list): # <8>
|
||||
future = executor.submit(download_one, cc,
|
||||
base_url, verbose) # <9>
|
||||
to_do_map[future] = cc # <10>
|
||||
done_iter = futures.as_completed(to_do_map) # <11>
|
||||
if not verbose:
|
||||
done_iter = tqdm.tqdm(done_iter, total=len(cc_list)) # <12>
|
||||
for future in done_iter: # <13>
|
||||
try:
|
||||
res = future.result() # <14>
|
||||
except requests.exceptions.HTTPError as exc: # <15>
|
||||
error_fmt = 'HTTP {res.status_code} - {res.reason}'
|
||||
error_msg = error_fmt.format(res=exc.response)
|
||||
except requests.exceptions.ConnectionError:
|
||||
error_msg = 'Connection error'
|
||||
else:
|
||||
error_msg = ''
|
||||
status = res.status
|
||||
|
||||
if error_msg:
|
||||
status = HTTPStatus.error
|
||||
counter[status] += 1
|
||||
if verbose and error_msg:
|
||||
cc = to_do_map[future] # <16>
|
||||
print(f'*** Error for {cc}: {error_msg}')
|
||||
|
||||
return counter
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many, DEFAULT_CONCUR_REQ, MAX_CONCUR_REQ)
|
||||
# end::FLAGS2_THREADPOOL[]
|
||||
127
20-futures/getflags/flags3_asyncio.py
Executable file
127
20-futures/getflags/flags3_asyncio.py
Executable file
@@ -0,0 +1,127 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of countries (with error handling).
|
||||
|
||||
asyncio async/await version using run_in_executor for save_flag.
|
||||
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from collections import Counter
|
||||
|
||||
import aiohttp
|
||||
import tqdm # type: ignore
|
||||
|
||||
from flags2_common import main, HTTPStatus, Result, save_flag
|
||||
|
||||
# default set low to avoid errors from remote site, such as
|
||||
# 503 - Service Temporarily Unavailable
|
||||
DEFAULT_CONCUR_REQ = 5
|
||||
MAX_CONCUR_REQ = 1000
|
||||
|
||||
|
||||
class FetchError(Exception):
|
||||
def __init__(self, country_code: str):
|
||||
self.country_code = country_code
|
||||
|
||||
async def get_flag(session: aiohttp.ClientSession,
|
||||
base_url: str,
|
||||
cc: str) -> bytes:
|
||||
url = f'{base_url}/{cc}/{cc}.gif'
|
||||
async with session.get(url) as resp:
|
||||
if resp.status == 200:
|
||||
return await resp.read()
|
||||
else:
|
||||
resp.raise_for_status()
|
||||
return bytes()
|
||||
|
||||
# tag::FLAGS3_ASYNCIO_GET_COUNTRY[]
|
||||
async def get_country(session: aiohttp.ClientSession, # <1>
|
||||
base_url: str,
|
||||
cc: str) -> str:
|
||||
url = f'{base_url}/{cc}/metadata.json'
|
||||
async with session.get(url) as resp:
|
||||
if resp.status == 200:
|
||||
metadata = await resp.json() # <2>
|
||||
return metadata.get('country', 'no name') # <3>
|
||||
else:
|
||||
resp.raise_for_status()
|
||||
return ''
|
||||
# end::FLAGS3_ASYNCIO_GET_COUNTRY[]
|
||||
|
||||
# tag::FLAGS3_ASYNCIO_DOWNLOAD_ONE[]
|
||||
async def download_one(session: aiohttp.ClientSession,
|
||||
cc: str,
|
||||
base_url: str,
|
||||
semaphore: asyncio.Semaphore,
|
||||
verbose: bool) -> Result:
|
||||
try:
|
||||
async with semaphore:
|
||||
image = await get_flag(session, base_url, cc) # <1>
|
||||
async with semaphore:
|
||||
country = await get_country(session, base_url, cc) # <2>
|
||||
except aiohttp.ClientResponseError as exc:
|
||||
if exc.status == 404:
|
||||
status = HTTPStatus.not_found
|
||||
msg = 'not found'
|
||||
else:
|
||||
raise FetchError(cc) from exc
|
||||
else:
|
||||
filename = country.replace(' ', '_') # <3>
|
||||
filename = f'{filename}.gif'
|
||||
loop = asyncio.get_running_loop()
|
||||
loop.run_in_executor(None,
|
||||
save_flag, image, filename)
|
||||
status = HTTPStatus.ok
|
||||
msg = 'OK'
|
||||
if verbose and msg:
|
||||
print(cc, msg)
|
||||
return Result(status, cc)
|
||||
# end::FLAGS3_ASYNCIO_DOWNLOAD_ONE[]
|
||||
|
||||
async def supervisor(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
concur_req: int) -> Counter[HTTPStatus]:
|
||||
counter: Counter[HTTPStatus] = Counter()
|
||||
semaphore = asyncio.Semaphore(concur_req)
|
||||
async with aiohttp.ClientSession() as session:
|
||||
to_do = [download_one(session, cc, base_url,
|
||||
semaphore, verbose)
|
||||
for cc in sorted(cc_list)]
|
||||
|
||||
to_do_iter = asyncio.as_completed(to_do)
|
||||
if not verbose:
|
||||
to_do_iter = tqdm.tqdm(to_do_iter, total=len(cc_list))
|
||||
for coro in to_do_iter:
|
||||
try:
|
||||
res = await coro
|
||||
except FetchError as exc:
|
||||
country_code = exc.country_code
|
||||
try:
|
||||
error_msg = exc.__cause__.message # type: ignore
|
||||
except AttributeError:
|
||||
error_msg = 'Unknown cause'
|
||||
if verbose and error_msg:
|
||||
print(f'*** Error for {country_code}: {error_msg}')
|
||||
status = HTTPStatus.error
|
||||
else:
|
||||
status = res.status
|
||||
|
||||
counter[status] += 1
|
||||
|
||||
return counter
|
||||
|
||||
|
||||
def download_many(cc_list: list[str],
|
||||
base_url: str,
|
||||
verbose: bool,
|
||||
concur_req: int) -> Counter[HTTPStatus]:
|
||||
coro = supervisor(cc_list, base_url, verbose, concur_req)
|
||||
counts = asyncio.run(coro) # <14>
|
||||
|
||||
return counts
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many, DEFAULT_CONCUR_REQ, MAX_CONCUR_REQ)
|
||||
47
20-futures/getflags/flags_asyncio.py
Executable file
47
20-futures/getflags/flags_asyncio.py
Executable file
@@ -0,0 +1,47 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of top 20 countries by population
|
||||
|
||||
asyncio + aiottp version
|
||||
|
||||
Sample run::
|
||||
|
||||
$ python3 flags_asyncio.py
|
||||
EG VN IN TR RU ID US DE CN MX JP BD NG ET FR BR PH PK CD IR
|
||||
20 flags downloaded in 1.07s
|
||||
|
||||
"""
|
||||
# tag::FLAGS_ASYNCIO_TOP[]
|
||||
import asyncio
|
||||
|
||||
from aiohttp import ClientSession # <1>
|
||||
|
||||
from flags import BASE_URL, save_flag, main # <2>
|
||||
|
||||
async def download_one(session: ClientSession, cc: str): # <3>
|
||||
image = await get_flag(session, cc)
|
||||
save_flag(image, f'{cc}.gif')
|
||||
print(cc, end=' ', flush=True)
|
||||
return cc
|
||||
|
||||
async def get_flag(session: ClientSession, cc: str) -> bytes: # <4>
|
||||
url = f'{BASE_URL}/{cc}/{cc}.gif'.lower()
|
||||
async with session.get(url) as resp: # <5>
|
||||
return await resp.read() # <6>
|
||||
# end::FLAGS_ASYNCIO_TOP[]
|
||||
|
||||
# tag::FLAGS_ASYNCIO_START[]
|
||||
def download_many(cc_list: list[str]) -> int: # <1>
|
||||
return asyncio.run(supervisor(cc_list)) # <2>
|
||||
|
||||
async def supervisor(cc_list: list[str]) -> int:
|
||||
async with ClientSession() as session: # <3>
|
||||
to_do = [download_one(session, cc) # <4>
|
||||
for cc in sorted(cc_list)]
|
||||
res = await asyncio.gather(*to_do) # <5>
|
||||
|
||||
return len(res) # <6>
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many)
|
||||
# end::FLAGS_ASYNCIO_START[]
|
||||
34
20-futures/getflags/flags_threadpool.py
Executable file
34
20-futures/getflags/flags_threadpool.py
Executable file
@@ -0,0 +1,34 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of top 20 countries by population
|
||||
|
||||
ThreadPoolExecutor version
|
||||
|
||||
Sample run::
|
||||
|
||||
$ python3 flags_threadpool.py
|
||||
DE FR BD CN EG RU IN TR VN ID JP BR NG MX PK ET PH CD US IR
|
||||
20 downloads in 0.35s
|
||||
|
||||
"""
|
||||
|
||||
# tag::FLAGS_THREADPOOL[]
|
||||
from concurrent import futures
|
||||
|
||||
from flags import save_flag, get_flag, main # <1>
|
||||
|
||||
def download_one(cc: str): # <2>
|
||||
image = get_flag(cc)
|
||||
save_flag(image, f'{cc}.gif')
|
||||
print(cc, end=' ', flush=True)
|
||||
return cc
|
||||
|
||||
def download_many(cc_list: list[str]) -> int:
|
||||
with futures.ThreadPoolExecutor() as executor: # <3>
|
||||
res = executor.map(download_one, sorted(cc_list)) # <4>
|
||||
|
||||
return len(list(res)) # <5>
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many) # <6>
|
||||
# end::FLAGS_THREADPOOL[]
|
||||
31
20-futures/getflags/flags_threadpool_futures.py
Executable file
31
20-futures/getflags/flags_threadpool_futures.py
Executable file
@@ -0,0 +1,31 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Download flags of top 20 countries by population
|
||||
|
||||
ThreadPoolExecutor example with ``as_completed``.
|
||||
"""
|
||||
from concurrent import futures
|
||||
|
||||
from flags import main
|
||||
from flags_threadpool import download_one
|
||||
|
||||
|
||||
# tag::FLAGS_THREADPOOL_AS_COMPLETED[]
|
||||
def download_many(cc_list: list[str]) -> int:
|
||||
cc_list = cc_list[:5] # <1>
|
||||
with futures.ThreadPoolExecutor(max_workers=3) as executor: # <2>
|
||||
to_do: list[futures.Future] = []
|
||||
for cc in sorted(cc_list): # <3>
|
||||
future = executor.submit(download_one, cc) # <4>
|
||||
to_do.append(future) # <5>
|
||||
print(f'Scheduled for {cc}: {future}') # <6>
|
||||
|
||||
for count, future in enumerate(futures.as_completed(to_do), 1): # <7>
|
||||
res: str = future.result() # <8>
|
||||
print(f'{future} result: {res!r}') # <9>
|
||||
|
||||
return count
|
||||
# end::FLAGS_THREADPOOL_AS_COMPLETED[]
|
||||
|
||||
if __name__ == '__main__':
|
||||
main(download_many)
|
||||
11
20-futures/getflags/requirements.txt
Normal file
11
20-futures/getflags/requirements.txt
Normal file
@@ -0,0 +1,11 @@
|
||||
aiohttp==3.7.4
|
||||
async-timeout==3.0.1
|
||||
attrs==20.3.0
|
||||
certifi==2020.12.5
|
||||
chardet==4.0.0
|
||||
idna==2.10
|
||||
requests==2.25.1
|
||||
urllib3==1.26.5
|
||||
tqdm==4.56.2
|
||||
multidict==5.1.0
|
||||
yarl==1.6.3
|
||||
92
20-futures/getflags/slow_server.py
Executable file
92
20-futures/getflags/slow_server.py
Executable file
@@ -0,0 +1,92 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""Slow HTTP server class.
|
||||
|
||||
This module implements a ThreadingHTTPServer using a custom
|
||||
SimpleHTTPRequestHandler subclass that introduces delays to all
|
||||
GET responses, and optionally returns errors to a fraction of
|
||||
the requests if given the --error_rate command-line argument.
|
||||
"""
|
||||
|
||||
import contextlib
|
||||
import os
|
||||
import socket
|
||||
import time
|
||||
from functools import partial
|
||||
from http import server, HTTPStatus
|
||||
from http.server import ThreadingHTTPServer, SimpleHTTPRequestHandler
|
||||
from random import random
|
||||
|
||||
|
||||
class SlowHTTPRequestHandler(SimpleHTTPRequestHandler):
|
||||
"""SlowHTTPRequestHandler adds delays and errors to test HTTP clients.
|
||||
|
||||
The optional error_rate argument determines how often GET requests
|
||||
receive a 418 status code, "I'm a teapot".
|
||||
If error_rate is .15, there's a 15% probability of each GET request
|
||||
getting that error.
|
||||
When the server believes it is a teapot, it refuses requests to serve files.
|
||||
|
||||
See: https://tools.ietf.org/html/rfc2324#section-2.3.2
|
||||
"""
|
||||
|
||||
def __init__(self, *args, error_rate=0.0, **kwargs):
|
||||
self.error_rate = error_rate
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
def do_GET(self):
|
||||
"""Serve a GET request."""
|
||||
time.sleep(.5)
|
||||
if random() < self.error_rate:
|
||||
self.send_error(HTTPStatus.IM_A_TEAPOT, "I'm a Teapot")
|
||||
else:
|
||||
f = self.send_head()
|
||||
if f:
|
||||
try:
|
||||
self.copyfile(f, self.wfile)
|
||||
finally:
|
||||
f.close()
|
||||
|
||||
# The code in the `if` block below, including comments, was copied
|
||||
# and adapted from the `http.server` module of Python 3.9
|
||||
# https://github.com/python/cpython/blob/master/Lib/http/server.py
|
||||
|
||||
if __name__ == '__main__':
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--bind', '-b', metavar='ADDRESS',
|
||||
help='Specify alternate bind address '
|
||||
'[default: all interfaces]')
|
||||
parser.add_argument('--directory', '-d', default=os.getcwd(),
|
||||
help='Specify alternative directory '
|
||||
'[default:current directory]')
|
||||
parser.add_argument('--error-rate', '-e', metavar='PROBABILITY',
|
||||
default=0.0, type=float,
|
||||
help='Error rate; e.g. use .25 for 25%% probability '
|
||||
'[default:0.0]')
|
||||
parser.add_argument('port', action='store',
|
||||
default=8000, type=int,
|
||||
nargs='?',
|
||||
help='Specify alternate port [default: 8000]')
|
||||
args = parser.parse_args()
|
||||
handler_class = partial(SlowHTTPRequestHandler,
|
||||
directory=args.directory,
|
||||
error_rate=args.error_rate)
|
||||
|
||||
# ensure dual-stack is not disabled; ref #38907
|
||||
class DualStackServer(ThreadingHTTPServer):
|
||||
def server_bind(self):
|
||||
# suppress exception when protocol is IPv4
|
||||
with contextlib.suppress(Exception):
|
||||
self.socket.setsockopt(
|
||||
socket.IPPROTO_IPV6, socket.IPV6_V6ONLY, 0)
|
||||
return super().server_bind()
|
||||
|
||||
# test is a top-level function in http.server omitted from __all__
|
||||
server.test( # type: ignore
|
||||
HandlerClass=handler_class,
|
||||
ServerClass=DualStackServer,
|
||||
port=args.port,
|
||||
bind=args.bind,
|
||||
)
|
||||
52
20-futures/primes/primes.py
Executable file
52
20-futures/primes/primes.py
Executable file
@@ -0,0 +1,52 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import math
|
||||
|
||||
|
||||
PRIME_FIXTURE = [
|
||||
(2, True),
|
||||
(142702110479723, True),
|
||||
(299593572317531, True),
|
||||
(3333333333333301, True),
|
||||
(3333333333333333, False),
|
||||
(3333335652092209, False),
|
||||
(4444444444444423, True),
|
||||
(4444444444444444, False),
|
||||
(4444444488888889, False),
|
||||
(5555553133149889, False),
|
||||
(5555555555555503, True),
|
||||
(5555555555555555, False),
|
||||
(6666666666666666, False),
|
||||
(6666666666666719, True),
|
||||
(6666667141414921, False),
|
||||
(7777777536340681, False),
|
||||
(7777777777777753, True),
|
||||
(7777777777777777, False),
|
||||
(9999999999999917, True),
|
||||
(9999999999999999, False),
|
||||
]
|
||||
|
||||
NUMBERS = [n for n, _ in PRIME_FIXTURE]
|
||||
|
||||
# tag::IS_PRIME[]
|
||||
def is_prime(n: int) -> bool:
|
||||
if n < 2:
|
||||
return False
|
||||
if n == 2:
|
||||
return True
|
||||
if n % 2 == 0:
|
||||
return False
|
||||
|
||||
root = math.isqrt(n)
|
||||
for i in range(3, root + 1, 2):
|
||||
if n % i == 0:
|
||||
return False
|
||||
return True
|
||||
# end::IS_PRIME[]
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
for n, prime in PRIME_FIXTURE:
|
||||
prime_res = is_prime(n)
|
||||
assert prime_res == prime
|
||||
print(n, prime)
|
||||
50
20-futures/primes/proc_pool.py
Executable file
50
20-futures/primes/proc_pool.py
Executable file
@@ -0,0 +1,50 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
"""
|
||||
proc_pool.py: a version of the proc.py example from chapter 20,
|
||||
but using `concurrent.futures.ProcessPoolExecutor`.
|
||||
"""
|
||||
|
||||
# tag::PRIMES_POOL[]
|
||||
import sys
|
||||
from concurrent import futures # <1>
|
||||
from time import perf_counter
|
||||
from typing import NamedTuple
|
||||
|
||||
from primes import is_prime, NUMBERS
|
||||
|
||||
class PrimeResult(NamedTuple): # <2>
|
||||
n: int
|
||||
flag: bool
|
||||
elapsed: float
|
||||
|
||||
def check(n: int) -> PrimeResult:
|
||||
t0 = perf_counter()
|
||||
res = is_prime(n)
|
||||
return PrimeResult(n, res, perf_counter() - t0)
|
||||
|
||||
def main() -> None:
|
||||
if len(sys.argv) < 2:
|
||||
workers = None # <3>
|
||||
else:
|
||||
workers = int(sys.argv[1])
|
||||
|
||||
executor = futures.ProcessPoolExecutor(workers) # <4>
|
||||
actual_workers = executor._max_workers # type: ignore # <5>
|
||||
|
||||
print(f'Checking {len(NUMBERS)} numbers with {actual_workers} processes:')
|
||||
|
||||
t0 = perf_counter()
|
||||
|
||||
numbers = sorted(NUMBERS, reverse=True) # <6>
|
||||
with executor: # <7>
|
||||
for n, prime, elapsed in executor.map(check, numbers): # <8>
|
||||
label = 'P' if prime else ' '
|
||||
print(f'{n:16} {label} {elapsed:9.6f}s')
|
||||
|
||||
time = perf_counter() - t0
|
||||
print(f'Total time: {time:.2f}s')
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
# end::PRIMES_POOL[]
|
||||
Reference in New Issue
Block a user