requests 实例

版权声明：猪小哥 https://blog.csdn.net/food_for_thought/article/details/82896397

# ===爬取京东
url = ''
try:
    r = requests.get(url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[:1000])  # 展示前一千字节的数据
except:
    print('爬取失败')


# ===爬取亚马逊
url = ''
try:
    kv = {'user-agent':'Mozilla/5.0'}
    r = requests.get(url, headers=kv)  # 浏览器伪装 Chrome/51.0.2704.63 Safari/537.36
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print('爬取失败')


# ===百度搜索
# 百度的关键词接口： http://www.baidu.com/s?wd=keyword
keyword = 'python'  # keyword即要搜索的词
try:
    kv = {'wd': keyword}
    r = requests.get('http://www.baidu.com/s', params=kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))  # 输出返回文本的长度
except:
    print('爬取失败')


# ===360搜索
# 360的关键词接口： http://www.so.com/s?q=keyword
keyword = 'python'
try:
    kv = {'q': keyword}
    r = requests.get('http://www.so.com/s', params=kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))  # 输出返回文本的长度
except:
    print('爬取失败')


# ===网络图片爬取
url = ''  # 图片地址
root = 'D://PICS//'  # 硬盘地址
path = root + url.split('/')[-1]  # 硬盘地址+图片地址最后一个以 / 为分割的名字
try:
    if not os.path.exists(root):
        os.mkdir(root)  # 数字模式创建目录
    if not os.path.exists(path):
        r = requests.get(url)
        with open(path, 'wb') as f:
            f.write(r.content)
            f.close()
            print('文件保存成功')
    else:
        print('文件已存在')
except:
    print('爬取失败')


# ===IP地址查询
url = 'http://m.ip138.com/ip.asp?ip=ipaddress'
try:
    r = requests.get(url + 'IP')
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[-500:])
except:
    print('爬取失败')