requests库入门之小爬虫

通用代码框架：

try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return "产生异常"

爬取某网页100次花费的时间

import requests
import time

def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        return r.text
    except:
        return "产生异常"

if __name__==‘__main__‘:
    url=‘http://www.baidu.com‘
    a=time.time()
    for i in range(100):
        getHTMLText(url)
    b=time.time()
    print(‘爬取100次需要花费的时间为%d秒‘ %(b-a))

爬取京东商品页面的爬取：

import requests

url=‘https://item.jd.com/5369026.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‘)

爬取有限制的网页：

import requests
url = ‘http://yzb.tju.edu.cn/xwzx/tkbs_xw/201609/t20160914_285521.htm‘
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‘)

百度关键词搜索：

import requests
keyword=‘Python‘
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))
except:
    print(‘爬取失败‘)

360关键词搜索全代码：

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‘)

图片爬取：

import requests
import os
url=‘http://image.nationalgeographic.com.cn/2017/0905/20170905114825283.jpg‘
root=‘E://pics//‘
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(‘文件保存成功‘)
    else:
        print(‘文件已存在‘)
except:
    print(‘爬取失败‘)

ip地址查询：

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‘)