from resoup import requests  # `import requests`와 호환됨.

from resoup import requests

with requests.Session() as session:
    ...  # cget, attempts 등 모든 기능 사용 가능

timeout 기본값: 120
headers 기본값: {
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
    "Accept-Encoding": "gzip, deflate, br",
    "Accept-Language": "ko-KR,ko;q=0.9",
    "Sec-Ch-Ua": '"Chromium";v="116", "Not)A;Brand";v="24", "Google Chrome";v="116"',
    "Sec-Ch-Ua-Mobile": "?0",
    "Sec-Ch-Ua-Platform": '"Windows"',
    "Sec-Fetch-Dest": "document",
    "Sec-Fetch-Mode": "navigate",
    "Sec-Fetch-Site": "none",
    "Sec-Fetch-User": "?1",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36",
}
attempts 기본값: 1
avoid_sslerror 기본값: False

>>> from resoup import requests
>>>
>>> from resoup import requests
>>> res = requests.get("https://httpbin.org/headers")
>>> res.json()['headers']
{'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
 'Accept-Encoding': 'gzip, deflate, br',
 'Accept-Language': 'ko-KR,ko;q=0.9',
 'Host': 'httpbin.org',
 'Sec-Ch-Ua': '"Chromium";v="116", "Not)A;Brand";v="24", "Google Chrome";v="116"',
 'Sec-Ch-Ua-Mobile': '?0',
 'Sec-Ch-Ua-Platform': '"Windows"',
 'Sec-Fetch-Dest': 'document',
 'Sec-Fetch-Mode': 'navigate',
 'Sec-Fetch-Site': 'none',
 'Sec-Fetch-User': '?1',
 'Upgrade-Insecure-Requests': '1',
 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
 'X-Amzn-Trace-Id': ...}

>>> from resoup import requests
>>>
>>> requests.get('https://some-not-working-website.com', attempts=10)
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
WARNING:root:Retring...
Traceback (most recent call last):
...
socket.gaierror: [Errno 11001] getaddrinfo failed

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
...
urllib3.exceptions.NameResolutionError: <urllib3.connection.HTTPSConnection object at ...>: Failed to resolve 'some-not-working-website.com' ([Errno 11001] getaddrinfo failed)

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
...
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='some-not-working-website.com', port=443): Max retries exceeded with url: / (Caused by NameResolutionError("<urllib3.connection.HTTPSConnection object at ...>: Failed to resolve 'some-not-working-website.com' ([Errno 11001] getaddrinfo failed)"))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
...
requests.exceptions.ConnectionError: HTTPSConnectionPool(host='some-not-working-website.com', port=443): Max retries exceeded with url: / (Caused by NameResolutionError("<urllib3.connection.HTTPSConnection object at ...>: Failed to resolve 'some-not-working-website.com' ([Errno 11001] getaddrinfo failed)"))

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
...
ConnectionError: Trying 10 times but failed to get data.
URL: https://some-not-working-website.com

>>> from resoup import requests
>>> requests.get('https://bufftoon.plaync.com')
---------------------------------------------------------------------------
SSLError                                  Traceback (most recent call last)
...
SSLError: HTTPSConnectionPool(host='bufftoon.plaync.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLError(1, '[SSL: UNSAFE_LEGACY_RENEGOTIATION_DISABLED] unsafe legacy renegotiation disabled (_ssl.c:1000)')))

<Response [200]>

>>> from resoup import requests
>>>
>>> requests.get('https://jsonplaceholder.typicode.com/todos/1').json()  # API that can send request in order to test. Don't execute this command unless you trust this API.
{'userId': 1, 'id': 1, 'title': 'delectus aut autem', 'completed': False}
>>> requests.post('https://jsonplaceholder.typicode.com/todos', json={
...     'title': 'foo',
...     'body': 'bar',
...     'userId': 1,
... }).json()
{'title': 'foo', 'body': 'bar', 'userId': 1, 'id': 201}  # Same with original requests library

>>> # 기기 사양과 인터넷 연결 품질에 따라 결과는 다를 수 있음
>>> import timeit
>>>
>>> timeit.timeit('requests.get("https://python.org")', number=10, setup='from resoup import requests')
1.1833231999917189 # 기기 사양과 인터넷 연결 품질에 따라 다름: 10번의 연결 모두 request를 보냄
>>> timeit.timeit('requests.cget("https://python.org")', number=10, setup='from resoup import requests')
0.10267569999268744 # : 처음 한 번만 request를 보내고 그 뒤는 캐시에서 값을 불러옴

>>> import asyncio
>>> 
>>> from resoup import requests
>>>
>>> res = asyncio.run(requests.aget('https://python.org'))
>>> res
<response [200]>

>>> import asyncio
>>> import timeit
>>>
>>> timeit.timeit('asyncio.run(requests.aget("https://python.org"))', number=10, setup='from resoup import requests; import asyncio')
0.8676127000362612 # 기기 사양과 인터넷 연결 품질에 따라 다름: 10번의 연결 모두 request를 보냄
>>> timeit.timeit('asyncio.run(requests.acget("https://python.org"))', number=10, setup='from resoup import requests; import asyncio')
0.11984489997848868 # 처음 한 번만 request를 보내고 그 뒤는 캐시를 불러옴

import asyncio
import time

from resoup import requests

async def masure_coroutine_time(coroutine):
    start = time.perf_counter()
    await coroutine
    end = time.perf_counter()

    print(end - start)

async def main():
    # 단일 request를 보낼 때(큰 차이 없음)

    req = requests.aget('https://python.org', run_in_executor=False)
    await masure_coroutine_time(req)  # 0.07465070000034757

    req = requests.aget('https://python.org')
    await masure_coroutine_time(req)  # 0.05844969999452587

    # 여러 request를 보낼 때(큰 속도 향상을 보임)

    reqs = (requests.aget(f'https://python.org/{i}', run_in_executor=False) for i in range(10))  # 더미 url을 만듦
    await masure_coroutine_time(asyncio.gather(*reqs))  # run_in_executor를 사용하지 않을 때: 느림(3.7874760999984574)

    reqs = (requests.aget(f'https://python.org/{i}') for i in range(10))  # 더미 url을 만듦
    await masure_coroutine_time(asyncio.gather(*reqs))  # run_in_executor를 사용할 때(기본값): 빠름(0.11582900000212248)

if __name__ == '__main__':
    asyncio.run(main())

>>> import requests
>>> requests.__name__
'requests'
>>> requests.__path__
['some path']
>>> requests.__cake__
'✨ 🍰 ✨'
>>>
>>> from resoup import requests
>>> requests.__name__  # 호환되지 않는 dunder method
'resoup.requests_proxy'  # requests와 값이 다름
>>> requests.__path__ # 사용할 수 없고 호환되지 않는 dunder method
AttributeError: module 'resoup.requests_' has no attribute '__path__'
>>> requests.__cake__  # 호환되는 dunder method
'✨ 🍰 ✨'

# 각 라인에서 윗줄과 아랫줄은 각각 requests를 import 할 때와 `resoup.requests`를 import할 때를 나타냅니다.

# requests 모듈 import
import requests
from resoup import requests  # 가능

# requests의 하위 모듈 import
import requests.models  # 가능
import resoup.requests.models  # 불가능!

# requests의 하위 모듈 import (w/ from .. import ...)
from request import models  # 가능
from resoup.requests import models  # 불가능!

# requests의 하위 모듈의 하위 구성 요소 import
from request.models import Response  # 가능
from resoup.requests.models import Response  # 불가능!

from request.models import Response  # 하위 모듈의 하위 구성 요소 import 사용

def is_response(instance):
    return isinstance(instance, Response)

# requests.models.Response로 바꾸기.
# 장점: 깔끔하고 error-prone하지 않음.
from resoup import requests  # requests 모듈 import
def is_response(instance):
    return isinstance(instance, requests.models.Response)  # requests.models.Response로 변경함

# Response 정의하기.
# 장점: 코드를 수정할 필요가 없음.
from resoup import requests
Response = requests.models.Response

def is_response(instance):
    return isinstance(instance, Response)

>>> # 두 모듈을 동시에 사용해야 하니 이름을 변경하겠습니다.
>>> import requests as orginal_requests
>>> from resoup import requests as utils_requsts
>>>
>>> # requests 모듈은 Response를 응답합니다.
>>> response1 = orginal_requests.get("https://peps.python.org/pep-0020/")  # 정적인 웹사이트
>>> print(response1)
<Response [200]>
>>> print(type(response1))  # Response 객체
<class 'requests.models.Response'>
>>> # resoup.requests모듈은 ResponseProxy를 응답합니다.
>>> response2 = utils_requsts.get("https://peps.python.org/pep-0020/")
>>> print(response2)
<Response [200]>
>>> print(type(response2))  # ResponseProxy 객체
<class 'resoup.response_proxy.ResponseProxy'>
>>>
>>> # 다음의 모든 검사들을 통과합니다.
>>> assert response1.text == response2.text
>>> assert response1.status_code == response2.status_code
>>> assert response1.url == response2.url
>>> assert response1.content == response2.content
>>>
>>> # 하지만 RequestsProxy에는 이러한 추가적인 기능들이 존재합니다.
>>> print(response2.soup())
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8"/>
...
<script src="../_static/wrap_tables.js"></script>
<script src="../_static/sticky_banner.js"></script>
</body>
</html>
>>> print(response2.soup_select('title'))
[<title>PEP 20 – The Zen of Python | peps.python.org</title>, <title>Following system colour scheme</title>, <title>Selected dark colour scheme</title>, <title>Selected light colour scheme</title>]
>>> print(response2.soup_select_one('p', no_empty_result=True).text)
Long time Pythoneer Tim Peters succinctly channels the BDFL’s guiding
principles for Python’s design into 20 aphorisms, only 19 of which
have been written down.
>>>
>>> from requests.models import Response
>>> # RequestsProxy는 Requsests의 subclass입니다.
>>> # 따라서 isinstance 검사를 통과합니다.
>>> isinstance(response2, Response)
True
>>> # 물론 subclass이기 때문에 '==' 검사는 통과하지 않습니다.
>>> type(response1) == type(response2)
False

>>> from resoup import requests
>>>
>>> response = requests.get("https://python.org")
>>> response.soup()  # BeatifulSoup에서 사용 가능한 모든 parameter 사용 가능
<!DOCTYPE html>
...
</body>
</html>

>>> import requests
>>> from bs4 import BeautifulSoup
>>>
>>> response = requests.get("https://python.org")
>>> BeautifulSoup(response.text)
<!DOCTYPE html>
<!DOCTYPE html>
...
</body>
</html>

>>> from resoup import requests
>>>
>>> response = requests.get("https://python.org")
>>> response.soup_select("p")
[<p><strong>Notice:</strong> While JavaScript is not essential for this website
...]

>>> import requests
>>> from bs4 import BeautifulSoup
>>>
>>> response = requests.get('https://python.org')
>>> soup = BeautifulSoup(response.text).select('p')
>>> soup
[<p><strong>Notice:</strong> While JavaScript is not essential for this website
...]

>>> from resoup import requests
>>>
>>> response = requests.get("https://python.org")
>>> response.soup_select("data-some-complex-and-error-prone-selector")
[]
>>>
>>> response = requests.get("https://python.org")
>>> response.soup_select(
...     "data-some-complex-and-error-prone-selector",
...     no_empty_result=True)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "...souptools.py", line 148, in soup_select
    raise EmptyResultError(
resoup.exceptions.EmptyResultError: Result of select is empty list("[]"). This error happens probably because of invalid selector or URL. Check if both selector and URL are valid. Set to False `no_empty_result` if empty list is intended. It may also because of selector is not matched with URL.
selector: data-some-complex-and-error-prone-selector, URL: https://www.python.org/

>>> from resoup import requests
>>>
>>> response = requests.get('https://python.org')
>>> response.soup_select_one('p strong', no_empty_result=True)
<strong>Notice:</strong>

>>> import requests
>>> from bs4 import BeautifulSoup
>>>
>>> response = requests.get('https://python.org')
>>> soup = BeautifulSoup(response.text, 'html.parser').select('p strong')
>>> if soup is None:  # no_empty_result 관련 확인 코드
...     raise Exception
...
>>> soup
<strong>Notice:</strong>

>>> from resoup import requests
>>>
>>> response = requests.get("https://python.org")
>>> print(response.soup_select_one("data-some-complex-and-error-prone-selector"))
None  # 실제로 None이 결과값으로 나오진 않고 그냥 조용히 종료됨.
>>>
>>> response = requests.get("https://python.org")
>>> response.soup_select_one(
...     "data-some-complex-and-error-prone-selector",
...     no_empty_result=True)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "...souptools.py", line 220, in soup_select_one
    raise EmptyResultError(
resoup.exceptions.EmptyResultError: Result of select_one is None. This error happens probably because of invalid selector or URL. Check if both selector and URL are valid. Set to False `no_empty_result` if empty list is intended. It may also because of selector is not matched with URL.  
selector: data-some-complex-and-error-prone-selector, URL: https://www.python.org/

>>> from resoup import requests
>>>
>>> response = requests.get('https://www.w3schools.com/xml/plant_catalog.xml')
>>> selected = response.xml_select('LIGHT', no_empty_result=True)
>>> selected
[<LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Sunny</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sunny</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sunny</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sunny</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sun</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>]

>>> from resoup import requests
>>> from functools import partial
>>>
>>> response = requests.get('https://www.w3schools.com/xml/plant_catalog.xml')
>>> # corespond to `.xml_select()`
>>> xml_select_partial = partial(response.soup_select, parser='xml')
>>> selected = xml_select_partial('LIGHT', no_empty_result=True)
>>> selected
[<LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Sunny</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sunny</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sunny</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sunny</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Sun or Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Sun</LIGHT>, <LIGHT>Mostly Shady</LIGHT>, <LIGHT>Shade</LIGHT>, <LIGHT>Shade</LIGHT>]

>>> from resoup import requests
>>> tags_list = requests.get("https://python.org").soup_select("p strong")
>>> [element.text for element in tags_list]
['Notice:', 'relaunched community-run job board']

>>> from resoup import requests
>>> tags_list = requests.get("https://python.org").soup_select("p strong")
>>> tags_list
[<strong>Notice:</strong>, <strong>relaunched community-run job board</strong>]
>>> type(tags_list)
<class 'resoup.broadcast_list.TagBroadcastList'>  # BroadcastList가 사용됨
>>> tags_list.text  # 브로드캐스팅
['Notice:', 'relaunched community-run job board']
>>>
>>> tags_list_with_no_broadcast_list = requests.get('https://python.org').soup_select('p', use_broadcast_list=False)
>>> type(tags_list_with_no_broadcast_list)
<class 'bs4.element.ResultSet'>  # BroadcastList가 사용되지 않음
>>> tags_list_with_no_broadcast_list.text
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "...element.py", line 2428, in __getattr__
    raise AttributeError(
AttributeError: ResultSet object has no attribute 'text'. You're probably treating a list of elements like a single element. Did you call find_all() when you meant to call find()?

>>> from resoup import requests
>>>
>>> tags_list = requests.get("https://python.org").soup_select("p", use_broadcase_list=False)
>>> type(tags_list)
bs4.element.ResultSet
>>> tags_list.text  # 브로드캐스팅 안 됨
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "...element.py", line 2428, in __getattr__
    raise AttributeError(
AttributeError: ResultSet object has no attribute 'text'. You're probably treating a list of elements like a single element. Did you call find_all() when you meant to call find()?

>>> from resoup import requests
>>> # 값 불러옴()
>>> tag_broadcast_list = requests.cget("https://www.python.org/community/logos/").soup_select("img")
>>> tag_broadcast_list
[<img alt="Python Software Foundation" class="psf-logo" src="/static/img/psf-logo.png"/>,
...
<img alt="Logo device only" src="https://s3.dualstack.us-east-2.amazonaws.com/pythondotorg-assets/media/community/logos/python-logo-only.png" style="height: 48px;"/>,
<img alt="/static/community_logos/python-powered-w-100x40.png" src="/static/community_logos/python-powered-w-100x40.png"/>,
<img alt="/static/community_logos/python-powered-h-50x65.png" src="/static/community_logos/python-powered-h-50x65.png"/>]
>>> # 정수 getitem
>>> tag_broadcast_list[0]
<img alt="Python Software Foundation" class="psf-logo" src="/static/img/psf-logo.png"/>
>>> # 슬라이싱
>>> tag_broadcast_list[3:5]
[<img alt="/static/community_logos/python-powered-w-100x40.png" src="/static/community_logos/python-powered-w-100x40.png"/>,
 <img alt="/static/community_logos/python-powered-h-50x65.png" src="/static/community_logos/python-powered-h-50x65.png"/>]
>>> # 문자열 getitem (브로드캐스팅 적용됨!)
>>> tag_broadcast_list["alt"]
['Python Software Foundation',
 'Combined logo',
 'Logo device only',
 '/static/community_logos/python-powered-w-100x40.png',
 '/static/community_logos/python-powered-h-50x65.png']

>>> from resoup import CustomDefaults
>>>
>>> requests = CustomDefaults(headers={'User-Agent': 'User Agent for Test'})
>>> requests.get('https://httpbin.org/headers').json()['headers']['User-Agent']
'User Agent for Test'