python requests网络爬取

# 1.京东商品页面的爬取
import requests
url = 'https://item.jd.com/100003717483.html'
try:
    r = requests.get(url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.encoding)
    print(r.text[:1000])
except:
    print('爬取失败')

# 2.亚马逊商品页面的爬取
import requests
url = 'https://www.amazon.cn/dp/B07H9VHC28/ref=sr_1_1?__mk_zh_CN=%E4%BA%9A%E9%A9%AC%E9%80%8A%E7%BD%91%E7%AB%99&keywords=iphone&pf_rd_i=664978051&pf_rd_m=A1U5RCOVU0NYF2&pf_rd_p=34bb0f29-ec94-4985-a530-186507566e35&pf_rd_r=5ZK12FC1ZZSB3T8Q917Y&pf_rd_s=merchandised-search-2&pf_rd_t=101&qid=1563191997&s=wireless&sr=1-1'
try:
    kv = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"}
    r = requests.get(url, headers=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.encoding,'1111111111111')
    print(r.text[1000:2000])
except:
    print('爬取失败')

# 3.百度/360搜索关键词提交
import requests
url = 'http://www.baidu.com/s'
kv = {'wd': "python"}
# url = 'http://www.so.com/s'
# kv = {'q': 'python'} 360
try:
    r = requests.get(url, params=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.encoding)
    print(len(r.text))
except:
    print('爬取失败')

# 4. 网络图片的爬取和存储
import requests
import os
url = 'https://www.natgeomedia.com/userfiles/sm/sm804_images_A1/8695/2019071539917113.jpg'
try:
    r = requests.get(url)
    print(r.status_code)
    print(r.content)
    with open('E:/1.jpg', 'wb') as f:
        f.write(r.content)
    f.close()
except:
    print("爬取失败")

# 5. IP地址归属地的自动查询
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")