Lib requests có gì hay mà dùng thay urllib

    International Domains and URLs
    Keep-Alive & Connection Pooling
    Sessions with Cookie Persistence
    Browser-style SSL Verification
    Basic/Digest Authentication
    Elegant Key/Value Cookies
    Automatic Decompression
    Unicode Response Bodies
    Multipart File Uploads
    Connection Timeouts
    Thread-safety

    Keep-Alive & Connection Pooling
    International Domains and URLs
    Sessions with Cookie Persistence
    Browser-style SSL Verification
    Automatic Content Decoding
    Basic/Digest Authentication
    Elegant Key/Value Cookies
    Automatic Decompression
    Unicode Response Bodies
    HTTP(S) Proxy Support
    Multipart File Uploads
    Streaming Downloads
    Connection Timeouts
    Chunked Requests
    .netrc Support

$ wc -l *| sort -nr
wc: __pycache__: Is a directory
   5049 total
    982 utils.py
    954 models.py
    767 sessions.py
    549 cookies.py
    533 adapters.py
    305 auth.py
    161 api.py
    131 __init__.py
    126 exceptions.py
    123 status_codes.py
    119 help.py
    105 structures.py
     72 compat.py
     42 _internal_utils.py
     34 hooks.py
     18 certs.py
     14 __version__.py
     14 packages.py

from . import sessions

def request(method, url, **kwargs):
    # By using the 'with' statement we are sure the session is closed, thus we
    # avoid leaving sockets open which can trigger a ResourceWarning in some
    # cases, and look like a memory leak in others.
    with sessions.Session() as session:
        return session.request(method=method, url=url, **kwargs)

def get(url, params=None, **kwargs):
    kwargs.setdefault('allow_redirects', True)
    return request('get', url, params=params, **kwargs)

def options(url, **kwargs):
    kwargs.setdefault('allow_redirects', True)
    return request('options', url, **kwargs)

def head(url, **kwargs):
    kwargs.setdefault('allow_redirects', False)
    return request('head', url, **kwargs)

def post(url, data=None, json=None, **kwargs):
    return request('post', url, data=data, json=json, **kwargs)

def put(url, data=None, **kwargs):
    return request('put', url, data=data, **kwargs)

def patch(url, data=None, **kwargs):
    return request('patch', url, data=data, **kwargs)

def delete(url, **kwargs):
    return request('delete', url, **kwargs)

Thread safety.
Connection pooling.
Client-side SSL/TLS verification.
File uploads with multipart encoding.
Helpers for retrying requests and dealing with HTTP redirects.
Support for gzip and deflate encoding.
Proxy support for HTTP and SOCKS.

>>> import urllib3
>>> http = urllib3.PoolManager()
>>> r = http.request('GET', 'http://httpbin.org/robots.txt')
>>> r.status
200
>>> r.data
'User-agent: *nDisallow: /denyn'

Python 3.6.9 (default, Nov  7 2019, 10:44:02)
[GCC 8.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import urllib.request
>>> from urllib.request import urlopen
>>> with urlopen("https://dantri.com") as f:
...     content = f.read()
...     print(content[:100])
...
Traceback (most recent call last):
  File "/usr/lib/python3.6/urllib/request.py", line 1318, in do_open
    ...
    self._sslobj.do_handshake()
ssl.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:852)
...
    raise URLError(err)
urllib.error.URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:852)>

>>> import requests
>>> requests.get("https://dantri.com")
Traceback (most recent call last):
  File "/home/hvn/py3/lib/python3.6/site-packages/urllib3/connectionpool.py", line 672, in urlopen
    ...
  File "/usr/lib/python3.6/ssl.py", line 689, in do_handshake
    self._sslobj.do_handshake()
ssl.SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:852)

>>> r = requests.get("https://gmail.com")
>>> r.url
'https://accounts.google.com/ServiceLogin?service=mail&passive=true&rm=false&continue=https://mail.google.com/mail/&ss=1&scc=1&ltmpl=default&ltmplcache=2&emr=1&osid=1'

>>> from urllib.request import urlopen
>>> r = urlopen("https://gmail.com")
>>> r.url
'https://accounts.google.com/ServiceLogin?service=mail&passive=true&rm=false&continue=https://mail.google.com/mail/&ss=1&scc=1&ltmpl=default&ltmplcache=2&emr=1&osid=1'

>>> import json
>>> from urllib.request import urlopen
>>> with urlopen("https://httpbin.org/ip") as f:
...     content = json.load(f)
...     print(content)
...
{'origin': '171.247.169.69'}

>>> import json
>>> from urllib.request import Request, urlopen
>>> with urlopen(
...   Request("https://httpbin.org/post", method="POST",
...           data=json.dumps({"name": "Pymi", "since": 2015}).encode('utf-8'),
...           headers={'Content-Type': "application/json"})
...           ) as resp:
...     print(json.load(resp)['json'])
...
{'name': 'Pymi', 'since': 2015}

>>> with urlopen("https://corona-stats.online/IT") as f:
...     print(f.read().decode("utf-8"))
...
╔═══════╤═══════╤═══════════╤═══════════╤════════╤════════╤═════════════╤═════════════╤═════════╤══════════╗
║       │ State │ Confirmed │ Recovered │ Deaths │ Active │ Mortality % │ Recovered % │ 1 Day ▲ │ 1 Week ▲ ║
╟───────┼───────┼───────────┼───────────┼────────┼────────┼─────────────┼─────────────┼─────────┼──────────╢
║ Italy │ Total │    31,506 │     2,941 │  2,503 │ 26,062 │        7.94 │        9.33 │ 3,526 ▲ │ 21,357 ▲ ║
╚═══════╧═══════╧═══════════╧═══════════╧════════╧════════╧═════════════╧═════════════╧═════════╧══════════╝

Stay safe. Stay inside.

Code: https://github.com/sagarkarira/coronavirus-tracker-cli
Twitter: https://twitter.com/ekrysis

Last Updated on: 18-Mar-2020 16:03 UTC