pyhthon爬虫

opener

1. 新建opener
   因为常规的urlopen()不支持代理，cookie和https等高级功能

   from urllib import request,parse
   import ssl
   import random
   
   ssl._create_default_https_context = ssl._create_unverified_context
   //创建一个httpHander对象处理https请求
   http_handler = request.HTTPSHandler()
   //创建一个opener对象
   opener=request.build_opener(http_handler)
   url='https//www.liepin.com'
   str={"key":"python"}
   url=url+parse.urlencode(str)
   //构建request请求
   request=request.Request(url)
   //调用自定义的opener对象发送request请求
   f=opener.open(request)
   //读取数据
   f.read().decode()

2. 给request添加请求头

   ua_list = [
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36",
       "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
       "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
       "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
       "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
       "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
   ]
   //随机获取一个头
   user_agent=random.choice(ua_list)
   request.add_header('user-agent',user_agent)

3. ProxyHandler处理器，设置代理ip

   from urllib import request,parse
   import urllib
   import ssl
   ssl._create_default_https_context = ssl._create_unverified_context  
   
   //构建一个有代理ip的handler
   http_handler=request.ProxyHandler({"http":"110.73.1.105:8123"})
   opener=request.build_opener(http_handler)
   request=request.Request(url)
   f=opener.open(request)
   f.read()

Requests

继承了urllib的所有特性，比urllib更简单

1. get请求

   import requests
   import random
   url='http://search.jiayuan.com/v2/index.php?key=%E7%90%86%E8%B4%A2&'
   qs={
   "sex":"f"
   }
   //从列表中读取一个header
   user_agent=random.choice(ua_list)
   headers={"user-agent":user_agent}
   
   #params 接收一个字典或者字符串的查询参数，字典类型自动转换为url编码，不需要urlencode()
   
   with requests.get(url=url,params=qs,headers=headers) as response:
   //response.text查看响应内容
       data=response.text
       //查看响应头部的编码
       print(response.encoding)
       with open('tb.html','w',encoding='utf-8') as fp:
           fp.write(data)
           fp.close()      

2. post请求

   with requests.post(url,data=data) as response:
   //json文件可以直接用requests.json
   print(response.json)

3. 如果要使用代理，加入proxies

   requests.get(peoxies=proxies)

页面解析

1. 正则表达式

   import re 
   with open('tb.html','r',encoding='utf-8') as fp:
       data=fp.read()
       re=r'"text": "(.*)",'
       reg=re.compile(re)
       res=reg.findall(data)
       print(res)

2. xml
   xml格式示例文档

   
   <bookstore> 
     <book category="cooking"> 
       <title lang="en">Everyday Italiantitle>  
       <author>Giada De Laurentiisauthor>  
       <year>2005year>  
       <price>30.00price> 
     book>  
     <book category="children"> 
       <title lang="en">Harry Pottertitle>  
       <author>J K. Rowlingauthor>  
       <year>2005year>  
       <price>29.99price> 
     book>  
     <book category="web"> 
       <title lang="en">XQuery Kick Starttitle>  
       <author>James McGovernauthor>  
       <author>Per Bothnerauthor>  
       <author>Kurt Cagleauthor>  
       <author>James Linnauthor>  
       <author>Vaidyanathan Nagarajanauthor>  
       <year>2003year>  
       <price>49.99price> 
     book> 
     <book category="web" cover="paperback"> 
       <title lang="en">Learning XMLtitle>  
       <author>Erik T. Rayauthor>  
       <year>2003year>  
       <price>39.95price> 
     book> 
   bookstore>

3. 选择器

   表达式	描述
   nodename	选取此节点的所有子节点
   /	从根节点开始选
   //	在全文档中找此节点
   .	当前节点
   ..	当前节点的父节点
   @	选取属性

范例

```
bookstore   选取 bookstore 元素的所有子节点(如果只有一个的话)。
/bookstore  选取根元素 bookstore。注释：假如路径起始于正斜杠( / )，则此路径始终代表到某元素的绝对路径！
bookstore/book  选取属于 bookstore 的直接子元素的所有 book 元素。
//book  选取所有 book 子元素，而不管它们在文档中的位置。
bookstore//book 选择属于 bookstore 元素的后代的所有 book 元素，而不管它们位于 bookstore 之下的什么位置。
bookstore//book/@lang   选取book元素的lang属性值。
bookstore//book[@class="book-css"]/title    选取class属性值为“book-css”的book元素的title。
//*[@class="bold"] 获取 class 值为 bold 的标签名
```

4. 读取xml文件

```
from lxml import etree

xml=etree.parse('data.xml')
titles=xml.xpath('//book/title')
authors=xml.xpath('//book/author')
prices=xml.xpath('//book/price')
for t in titles:
    print(t.text)
```

5. lxml读取html文件

```
from lxml import etree
//增加parser参数
parser=etree.HTMLParser(encoding='utf-8')
htmlelement=etree.parse('liepin.html',parser=parser)
html_string=etree.tostring(htmlelement,encoding='utf-8').decode(encoding='utg-8')
//读取innertext
links=htmlelement.xpath('//div/div/span/a')
for a in links:
    print(a.text)

//读取属性的值
with open('liepin.html','r',encoding='utf-8') as fp:
    content=fp.read()
    html=etree.HTML(content)
    links=html.xpath('//div/div/span/@title')
    for title in titles:
        print(title)
```