爬虫入门

1、搜索结果爬取(未解析)

#coding:utf-8
import requests
url="http://www.baidu.com/s"
try:
    #kv={'user-agent':'Mozilla/5.0'}
    kv={'wd':'Python'}
    r=requests.get(url,params=kv)
    print r.status_code
    r.raise_for_status()
    r.encoding=r.apparent_encoding
    print len(r.text)
except:
    print '产生异常'

2、爬取图片

#coding:utf-8
import requests
import os
url="http:image.nationalgeographic.com.cn/2017/0211/20170211061910157.jpg"
root="/Users/wangkun/Desktop/DEMO1/"
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'

3、IP归属地查询

#coding:utf-8
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'

 4、beautifulsoup解析

import requests
from bs4 import BeautifulSoup
r=requests.get('http://python123.io/ws/demo.html')
demo=r.text
soup=BeautifulSoup(demo,'html.parser')
soup.prettify()#
for link in soup.find_all('a'):
    print(link.get('href'))

print(soup.a.next_siblings)

 5、爬取并解析大学排名,print输出(数据结构结果)

#coding:utf-8
import requests
from bs4 import BeautifulSoup
import bs4
import re
def getHTMLText(url):
    try:
        r=requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding=r.apparent_encoding
        #print(r.text)
        return r.text
    except:
        return ''


def fillList(ulist,html):
    soup=BeautifulSoup(html,'html.parser')
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):
            tds=tr('td')
            ulist.append([tds[0].string,tds[1].string,tds[3].string])
    #print(ulist)

def printList(ulist,num):
    print("{:^10}\t{:^6}\t{:^10}".format('排名','学校名称','总分'))
    for i in range(num):
        u=ulist[i]
        print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]))
    return("Suc"+str(num))


uinfo=[]
url="http://www.zuihaodaxue.cn/shengyuanzhiliangpaiming2018.html"
html=getHTMLText(url)
fillList(uinfo,html)
printList(uinfo,20) #20所大学的信息

 

posted @ 2018-08-09 22:32  Elpsywk  阅读(261)  评论(0编辑  收藏  举报