requests

hh_hu

已于 2023-03-16 09:42:57 修改

阅读量65

点赞数

文章标签： python Powered by 金山文档

于 2023-03-15 22:28:05 首次发布

本文链接：https://blog.csdn.net/huizhuo_hu/article/details/129571606

版权

import requests
kv={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
r=requests.get("https://item.jd.com/100041239020.html",headers=kv )
print(r.status_code)
print(r.text)

import requests
kv={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
url='https://item.jd.com/100041239020.html'
try:

    r=requests.get(url,headers=kv )
    r.raise_for_status()
    r.encoding=r.apparent_encoding
print(r.status_code)
print(r.text[:1000])
except:
print("爬取失败")

import requests
# kv={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
url='https://www.amazon.cn/dp/B0BX5R554N/'
try:
    r=requests.get(url)
# r.raise_for_status()
    r.encoding=r.apparent_encoding
print(r.status_code)
print(r.text[:1000])
except:
print("爬取失败")

import requests
kv={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
url='https://www.amazon.cn/dp/B0BX5R554N/'
try:
    r=requests.get(url, headers=kv)
    r.raise_for_status()
# r.encoding=r.apparent_encoding
    print(r.status_code)
print(r.request.headers)
print(r.text[:1000])
except:
print("爬取失败")

import requests
path = "E:\\re\\abc.jpg"
hd={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
url='http://img0.dili360.com/pic/2020/01/06/5e130172402b79y44941505_t.jpg@!rw9'
try:
    r=requests.get(url, headers=hd)
    r.raise_for_status()
    print(r.status_code)
    with open(path,'wb') as f:
        f.write(r.content)
    f.close()
except:
    print("爬取失败")

百度不成功

# https://www.baidu.com/s?wd=keyword
# https://www.baidu.com/s?ie=utf-8&f=3&rsv_bp=1&rsv_idx=1&tn=baidu&wd=%E4%B8%AD%E5%9B%BD
# https://www.so.com/s?q=keyword

import requests
kv={'wd':'泰国'}
hd={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
url='https://www.baidu.com/s?ie=utf-8&f=3&rsv_bp=1&rsv_idx=1&tn=baidu&'
try:
    r=requests.get(url, params=kv,headers=hd)
    r.raise_for_status()
    r.encoding=r.apparent_encoding
    print(r.status_code)
    print(r.request.url)
    print(r.text[:1000])
except:
    print("爬取失败")

会验证

import requests
hd={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
ip='112.96.59.100'
url='https://www.ipshudi.com/'+ip+'.htm'
try:
    r=requests.get(url, headers=hd)
    r.raise_for_status()
    print(r.status_code)
    print(r.text[1500:3000])
except:
    print("爬取失败")

import requests
kv={'q':'泰国'}
hd={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.49'}
url='https://www.so.com/s'
try:
    r=requests.get(url, params=kv,headers=hd)
    r.raise_for_status()
    r.encoding=r.apparent_encoding
    print(r.status_code)
    print(r.request.url)
    print(r.text[:1000])
except:
    print("爬取失败")