import urllib3

# 禁用警告（在生产环境中不建议这么做）
urllib3.disable_warnings()

# 创建 poolmanager 实例
http = urllib3.poolmanager()

# 发送get请求
response = http.request('get', 'https://api.example.com/users')

# 打印响应状态和数据
print(response.status)
print(response.data.decode('utf-8'))

import json

data = {'username': 'john', 'password': 'secret'}
encoded_data = json.dumps(data).encode('utf-8')

response = http.request(
'post',
'https://api.example.com/login',
body=encoded_data,
headers={'content-type': 'application/json'}
)

print(response.status)
print(response.data.decode('utf-8'))

from urllib3.util.retry import retry
from urllib3.util.timeout import timeout

retries = retry(total=3, backoff_factor=0.1)
timeout = timeout(connect=5.0, read=10.0)

http = urllib3.poolmanager(retries=retries, timeout=timeout)

response = http.request('get', 'https://api.example.com/users')

# 创建一个连接池
pool = urllib3.httpconnectionpool('api.example.com', maxsize=10)

# 使用连接池发送请求
response = pool.request('get', '/users')

import certifi

http = urllib3.poolmanager(
cert_reqs='cert_required',
ca_certs=certifi.where()
)

response = http.request('get', 'https://api.example.com/users')

import requests

# 发送get请求
response = requests.get('https://api.example.com/users')

# 打印响应状态和内容
print(response.status_code)
print(response.text)

# 自动解析json响应
data = response.json()
print(data)

data = {'username': 'john', 'password': 'secret'}
response = requests.post('https://api.example.com/login', json=data)

print(response.status_code)
print(response.json())

headers = {'user-agent': 'myapp/1.0'}
response = requests.get('https://api.example.com/users', headers=headers)

# 创建会话
session = requests.session()

# 登录
login_data = {'username': 'john', 'password': 'secret'}
session.post('https://api.example.com/login', json=login_data)

# 使用同一会话发送后续请求
response = session.get('https://api.example.com/dashboard')

files = {'file': open('document.pdf', 'rb')}
response = requests.post('https://api.example.com/upload', files=files)

from requests.adapters import httpadapter
from requests.packages.urllib3.util.retry import retry

retry_strategy = retry(
total=3,
backoff_factor=0.1,
status_forcelist=[429, 500, 502, 503, 504]
)
adapter = httpadapter(max_retries=retry_strategy)
session = requests.session()
session.mount('https://', adapter)
session.mount('http://', adapter)

response = session.get('https://api.example.com/users', timeout=5)

with requests.get('https://api.example.com/large-file', stream=true) as r:
r.raise_for_status()
with open('large-file.zip', 'wb') as f:
for chunk in r.iter_content(chunk_size=8192):
f.write(chunk)

import requests
from bs4 import beautifulsoup

def scrape_website(url):
headers = {
'user-agent': 'mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/91.0.4472.124 safari/537.36'
}

try:
response = requests.get(url, headers=headers, timeout=10)
response.raise_for_status() # 如果请求不成功则抛出异常

soup = beautifulsoup(response.text, 'html.parser')

# 提取标题
title = soup.title.string if soup.title else 'no title found'

# 提取所有段落文本
paragraphs = [p.text for p in soup.find_all('p')]

# 提取所有链接
links = [a['href'] for a in soup.find_all('a', href=true)]

return {
'title': title,
'paragraphs': paragraphs,
'links': links
}
except requests.requestexception as e:
print(f"请求错误: {e}")

return none

# 使用示例
result = scrape_website('https://example.com')
if result:
print(f"title: {result['title']}")
print(f"number of paragraphs: {len(result['paragraphs'])}")
print(f"number of links: {len(result['links'])}")