Python爬虫入门-2

robots.txt :
UA:
1.指定url
2.发起请求
3.获取页面数据
4.数据解析
5.持久化存储
bs4:
- 实例化bs对象,将页面源码数据加载到该对象中
- 定位标签:find('name',class_='xxx') findall() select()
- 将标签中的文本内容获取 string text get_text() a['href']

环境安装:pip install lxml
解析原理:

获取页面源码数据
实例化一个etree的对象,并且将页面源码数据加载到该对象中
调用该对象的xpath方法进行指定标签的定位
注意:xpath函数必须结合着xpath表达式进行标签定位和内容捕获

/html/head/title
//head/title
//title

<html lang="en">
<head>
    <meta charset="UTF-8" />
    <title>测试bs4</title>
</head>
<body>
    <div>
        <p>百里守约</p>
    </div>
    <div class="song">
        <p>李清照</p>
        <p>王安石</p>
        <p>苏轼</p>
        <p>柳宗元</p>
        <a href="http://www.song.com/" title="赵匡胤" target="_self">
            <span>this is span</span>
        宋朝是最强大的王朝，不是军队的强大，而是经济很强大，国民都很有钱</a>
        <a href="" class="du">总为浮云能蔽日,长安不见使人愁</a>
        <img src="http://www.baidu.com/meinv.jpg" alt="" />
    </div>
    <div class="tang">
        <ul>
            <li><a href="http://www.baidu.com" title="qing">清明时节雨纷纷,路上行人欲断魂,借问酒家何处有,牧童遥指杏花村</a></li>
            <li><a href="http://www.163.com" title="qin">秦时明月汉时关,万里长征人未还,但使龙城飞将在,不教胡马度阴山</a></li>
            <li><a href="http://www.126.com" alt="qi">岐王宅里寻常见,崔九堂前几度闻,正是江南好风景,落花时节又逢君</a></li>
            <li><a href="http://www.sina.com" class="du">杜甫</a></li>
            <li><a href="http://www.dudu.com" class="du">杜牧</a></li>
            <li><b>杜小月</b></li>
            <li><i>度蜜月</i></li>
            <li><a href="http://www.haha.com" id="feng">凤凰台上凤凰游,凤去台空江自流,吴宫花草埋幽径,晋代衣冠成古丘</a></li>
        </ul>
    </div>
</body>
</html>

#项目需求：解析58二手房的相关数据
import requests
from lxml import etree

url = 'https://bj.58.com/shahe/ershoufang/?utm_source=market&spm=u-2d2yxv86y3v43nkddh1.BDPCPZ_BT&PGTID=0d30000c-0047-e4e6-f587-683307ca570e&ClickID=1'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath('//ul[@class="house-list-wrap"]/li')
fp = open('58.csv','w',encoding='utf-8')
for li in li_list:
    title = li.xpath('./div[2]/h2/a/text()')[0]
    price = li.xpath('./div[3]//text()')
    price = ''.join(price)
    fp.write(title+":"+price+'\n')
fp.close()
print('over')

# ctrl+shift+x
# - 解析图片数据：http://pic.netbian.com/4kmeinv/
import requests
from lxml import etree
import os
import urllib

url = 'http://pic.netbian.com/4kmeinv/'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
response = requests.get(url=url,headers=headers)
#response.encoding = 'utf-8'
if not os.path.exists('./imgs'):
    os.mkdir('./imgs')
page_text = response.text

tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="slist"]/ul/li')
for li in li_list:
    img_name = li.xpath('./a/b/text()')[0]
    #处理中文乱码
    img_name = img_name.encode('iso-8859-1').decode('gbk')
    img_url = 'http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
    img_path = './imgs/'+img_name+'.jpg'
    urllib.request.urlretrieve(url=img_url,filename=img_path)
    print(img_path,'下载成功!')
print('over!!!')

#【重点】下载煎蛋网中的图片数据：http://jandan.net/ooxx
#数据加密  (反爬机制)
import requests
from lxml import etree
import base64
import urllib


headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'http://jandan.net/ooxx'
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
img_hash_list = tree.xpath('//span[@class="img-hash"]/text()')
for img_hash in img_hash_list:
    img_url = 'http:'+base64.b64decode(img_hash).decode()
    img_name = img_url.split('/')[-1]
    urllib.request.urlretrieve(url=img_url,filename=img_name)

import random
#爬取站长素材中的简历模板
import requests
import random
from lxml import etree
headers = {
    'Connection':'close', #当请求成功后,马上断开该次请求(及时释放请求池中的资源)
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'http://sc.chinaz.com/jianli/free_%d.html'
for page in range(1,4):
    if page == 1:
        new_url = 'http://sc.chinaz.com/jianli/free.html'
    else:
        new_url = format(url%page)
    
    response = requests.get(url=new_url,headers=headers)
    response.encoding = 'utf-8'
    page_text = response.text

    tree = etree.HTML(page_text)
    div_list = tree.xpath('//div[@id="container"]/div')
    for div in div_list:
        detail_url = div.xpath('./a/@href')[0]
        name = div.xpath('./a/img/@alt')[0]

        detail_page = requests.get(url=detail_url,headers=headers).text
        tree = etree.HTML(detail_page)
        download_list  = tree.xpath('//div[@class="clearfix mt20 downlist"]/ul/li/a/@href')
        download_url = random.choice(download_list)
        data = requests.get(url=download_url,headers=headers).content
        fileName = name+'.rar'
        with open(fileName,'wb') as fp:
            fp.write(data)
            print(fileName,'下载成功')

#解析所有的城市名称
import requests
from lxml import etree
headers = {
    'Connection':'close', #当请求成功后,马上断开该次请求(及时释放请求池中的资源)
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
url = 'https://www.aqistudy.cn/historydata/'
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="bottom"]/ul/li |  //div[@class="bottom"]/ul/div[2]/li')
for li in li_list:
    city_name = li.xpath('./a/text()')[0]
    print(city_name)

#设置请求的代理ip: www.goubanjia.com  快代理  西祠代理
#代理ip的类型必须和请求url的协议头保持一致
url = 'https://www.baidu.com/s?wd=ip'

page_text = requests.get(url=url,headers=headers,proxies={'https':'61.7.170.240:8080'}).text

with open('./ip.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

robots
UA
数据加密
懒加载
代理ip

posted @ 2019-02-28 16:47 一只待宰的程序猿阅读(257) 评论(0) 编辑收藏举报

刷新页面返回顶部

一只待宰的程序猿

Python爬虫入门-2

公告