Requests库网络爬虫实战

import requests
url = "https://item.jd.com/100004770237.html"
try:
   r = requests.get(url)
   r.raise_for_status()
   r.encoding = r.apparent_encoding
   print(r.text[:1000])
except:
    print("爬取失败")　

import requests
url = "https://www.amazon.cn/dp/B071HXVPXG/ref=lp_659039051_1_2?s=books&ie=UTF8&qid=1580353560&sr=1-2"
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")　

import requests
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))   
except:
    print("爬取失败")

import requests
import os
url = "http://img1.3lian.com/2015/w7/97/d/25.jpg"
#设置爬取图片的存储位置及名称，名称可以使用图片原有的名称也可以自定义
root = "E://python//"
path = root + url.split(‘/‘)[-1]
try:
    if not os.path.exists(root):
        os.mkdir(root)
    if not os.path.exists(path):
        r = requests.get(url)
        with open (path , ‘wb‘ ) as f:
            f.write(r.content)
            f.close()
            print("文档保存成功")
    else:
        print("文件已经存在在")
except:
    print("爬取失败")
        

import requests
url = "http://m.ip138.com/ip.asp?ip="
try:
    r = requests.get(url+‘202.204.80.112‘)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[-500:])
except:
    print("爬取失败")