1
2
3
4
5
6

import requests
r = requests.get("http://www.baidu.com")
r.status_code
200
r.encoding = 'utf-8'
r.text

1
2

type(r)
<class 'requests.models.Response'>

1

r.headers

1
2
3
4
5
6

import requests
r = requests.head('http://httpbin.org/get')
r.headers
{'Connection': 'close', 'Content-Length': '314', 'Access-Control-Allow-Credentials': 'true', 'Access-Control-Allow-Origin': '*', 'Content-Type': 'application/json', 'Date': 'Sat, 24 Jan 2026 05:21:20 GMT', 'Server': 'gunicorn/19.9.0'}
r.text
''

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

payload = {'key1': 'value1', 'key2': 'value2'}
r = requests.post('http://httpbin.org/post', data = payload)
print(r.text)
{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "key1": "value1", 
    "key2": "value2"
  }, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate, zstd", 
    "Content-Length": "23", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.32.3", 
    "X-Amzn-Trace-Id": "Root=1-697457cd-5152d26b1cc17af764bd2e52"
  }, 
  "json": null, 
  "origin": "178.249.213.181", 
  "url": "http://httpbin.org/post"
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

payload = {'key1': 'value1', 'key2': 'value2'}
r = requests.put('http://httpbin.org/put', data = payload)
print(r.text)
{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "key1": "value1", 
    "key2": "value2"
  }, 
  "headers": {
    "Accept": "*/*", 
    "Accept-Encoding": "gzip, deflate, zstd", 
    "Content-Length": "23", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "python-requests/2.32.3", 
    "X-Amzn-Trace-Id": "Root=1-6974589a-5736a6a46a39117944a8b31a"
  }, 
  "json": null, 
  "origin": "178.249.213.181", 
  "url": "http://httpbin.org/put"
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

import requests

def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "产生异常"

if __name__ == "__main__":
    url = "http://www.baidu.com"
    print(getHTMLText(url))

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24

import requests
import time

url = "http://httpbin.org/get"

success_count = 0

start_time = time.time()

for i in range(100):
    try:
        r = requests.get(url, timeout=5)
        if r.status_code == 200:
            success_count += 1
    except Exception as e:
        print(f"第 {i+1} 次请求失败：", e)

end_time = time.time()

total_time = end_time - start_time

print("成功爬取的次数：", success_count)
print("总耗时：{:.4f} 秒".format(total_time))
print("平均每次耗时：{:.4f} 秒".format(total_time / success_count))

1
2
3
4
5
6

# 注释
* 代表所有
/ 代表根目录

User-agent: *  代表哪些爬虫
Disallow: /	   代表爬虫不允许访问的资源

1
2
3
4
5
6
7
8
9

import requests
url = ""
try:
    r = requests.get(url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[:1000])
except:
    print("爬取失败")

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

import requests
url = "https://www.amazon.com/dp/B0FWV56H48?ref=dlx_deals_dg_dcl_B0FWV56H48_dt_sl14_c6_pi&pf_rd_r=VDKDWZ93A7PAEC5W2WZZ&pf_rd_p=b343bf4e-9a59-4902-9f89-b3ece0bb2fc6&th=1"
try:
    kv = {'user-agent':'Mozilla/5.0'}
    r = requests.get(url, headers=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print("爬取失败")

1
2
3
4
5

import requests
kv = {'wd':'Python'}
r= requests.get("https://www.baidu.com/s", params = kv)
r.status_code
r.request.url

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19

import requests

kv = {'wd': 'Python'}

# 定义请求头，核心是添加 User-Agent 伪装浏览器
headers = {
    # 模拟 Chrome 浏览器的 User-Agent
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
    # 可选：添加 Referer 字段，表明请求来自百度首页，进一步提升真实性
    'Referer': 'https://www.baidu.com/'
}

# 发送 GET 请求，同时传入 params（参数）和 headers（请求头）
# 注意：网址使用 https（百度默认跳转 https，更稳定）
r = requests.get("https://www.baidu.com/s", params=kv, headers=headers)

r.status_code
r.request.url
r.text[:100]

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

import requests

keyword = "Python"  # 保留图片里的关键词定义
try:
    # 1. 构造搜索参数（对应图片里的kv）
    kv = {'wd': keyword}
    
    # 2. 定义请求头（融合你提供的伪装浏览器配置）
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
        'Referer': 'https://www.baidu.com/'
    }
    
    # 3. 发送HTTPS请求（融合你的请求方式，同时保留图片里的params参数）
    r = requests.get("https://www.baidu.com/s", params=kv, headers=headers)
    
    # 4. 保留图片里的功能：打印请求URL
    print("请求的完整URL:", r.request.url)
    
    # 5. 检查请求是否成功（图片里的raise_for_status()）
    r.raise_for_status()
    
    # 6. 保留你的需求：打印响应状态码、文本前100字符
    print("响应状态码:", r.status_code)
    print("响应文本前100字符:\n", r.text[:100])
    
    # 7. 保留图片里的功能：打印响应文本长度
    print("响应文本总长度:", len(r.text))

except:
    # 图片里的异常处理：捕获所有错误并提示
    print("爬取失败")

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43

import requests
import os

# 图片目标 URL
url = "https://img0.dili360.com/pic/2025/12/31/6954ebc48ed745o09300347.jpg"

# 图片保存路径（自动提取文件名、创建文件夹）
root = "D:/pics/"  
path = root + url.split('/')[-1]

# 定义请求头，解决 403 防盗链问题
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
    'Referer': 'https://www.dili360.com/'
}

try:
    # 1. 判断文件夹是否存在，不存在则创建
    if not os.path.exists(root):
        os.mkdir(root)
        print(f"文件夹不存在，已创建：{root}")
    
    # 2. 判断文件是否存在，不存在则下载保存
    if not os.path.exists(path):
        # 3. 发送 GET 请求，携带 headers 伪装浏览器（补充遗漏的 headers）
        r = requests.get(url, headers=headers)
        
        # 4. 校验请求是否成功（非 200 状态码直接抛出异常）
        r.raise_for_status()
        
        # 5. 二进制写入保存图片（移除冗余的 f.close()）
        with open(path, 'wb') as f:
            f.write(r.content)
        
        print(f"文件保存成功，已保存至：{path}")
        print(f"响应状态码：{r.status_code}")
    else:
        # 6. 文件已存在时的提示
        print(f"文件已存在，无需重复下载：{path}")

except Exception as e:
    # 7. 捕获所有错误并给出详细提示
    print(f"爬取/保存失败，错误信息：{str(e)}")

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36

import requests

# 第三方 IP 查询接口（稳定有效，无严格反爬）
base_url = "http://ip-api.com/json/"
target_ip = "202.204.80.112"

# 拼接 URL（该接口支持直接在 URL 后拼接 IP）
url = base_url + target_ip

# 可选：添加请求头，提升真实性
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
}

try:
    r = requests.get(url, headers=headers, timeout=10)
    r.raise_for_status()
    r.encoding = 'utf-8'
    
    # 解析 JSON 数据（该接口返回标准 JSON，无解析报错）
    ip_result = r.json()
    
    # 打印完整结果和核心信息
    print("请求成功，响应状态码：", r.status_code)
    print("=====================================")
    print("完整 JSON 查询结果：\n", ip_result)
    print("=====================================")
    print("核心查询信息：")
    print(f"  IP 地址：{ip_result.get('query', '未知')}")
    print(f"  国家：{ip_result.get('country', '未知')}")
    print(f"  地区：{ip_result.get('regionName', '未知')}")
    print(f"  城市：{ip_result.get('city', '未知')}")
    print(f"  运营商：{ip_result.get('isp', '未知')}")

except Exception as e:
    print("请求失败，错误信息：", str(e))