import requests
url = "http://www.baidu.com"
try:
r = requests.get(url)
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text)
except:
print("爬取失败!")
import requests
url = "https://www.amazon.cn/dp/B073LJR2JF/ref=cngwdyfloorv2_recs_0?pf_rd_p=4940946c-0b2b-498c-9e03-31cf7dae70ec&pf_rd_s=desktop-2&pf_rd_t=36701&pf_rd_i=desktop&pf_rd_m=A1AJ19PSB66TGU&pf_rd_r=0VBSDZTEFWPWMG7F7X7M&pf_rd_r=0VBSDZTEFWPWMG7F7X7M&pf_rd_p=4940946c-0b2b-498c-9e03-31cf7dae70ec"
try:
d = {'user-agent':'Mozilla/5.0'}
r = requests.get(url,headers = d)
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[0:1000])
except:
print("失败")
import requests
try:
d = {'kw':"python"}
url = "http://www.baidu.com"
r = requests.get(url,params=d)
r.raise_for_status()
print(len(r.text))
print(r.text)
except:
print("爬取失败!")
import requests
import os
root = "C://Users/root/Desktop/web/"
url = ""
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("文件已关闭,保存!")
else:
print("文件已存在")
print(path)
except:
print("爬取失效")
import requests
url = "http://m.ip.138.com/ip.asp?ip="
try:
d = {}
r = requests.get(url+'123.129.244.228')
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[-500:])
except:
print("爬取失败!")