Python爬虫(三)_urllib2:get和post请求

#-*- coding:utf-8 -*-
#06.urllib2_urlencode.py
import urllib2
import urllib

word = {"wd":"传智播客"}

#通过urllib.urlencode()方法，将字典键值对按URL编码转换，从而能被web服务器接受
encode = urllib.urlencode(word)

print(encode)
#通过urllib.unquote()方法，把URL编码字符串，转换回原始字符串

print(urllib.unquote("wd=%E4%BC%A0%E6%99%BA%E6%92%AD%E5%AE%A2"))

#-*- coding:utf-8 -*-
#07.urllib2_get.py

import urllib
import urllib2

url = "http://www.baidu.com/s"
word = {"wd":"传智播客"}
word = urllib.urlencode(word) #转换成url编码格式(字符串)

newurl = url + "?" + word

headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36"}

request = urllib2.Request(newurl,headers = headers)

response = urllib2.urlopen(request)

print(response.read())

# 模拟 main 函数
if __name__ == "__main__":

    kw = raw_input("请输入需要爬取的贴吧:")
    # 输入起始页和终止页，str转成int类型
    beginPage = int(raw_input("请输入起始页："))
    endPage = int(raw_input("请输入终止页："))

    url = "http://tieba.baidu.com/f?"
    key = urllib.urlencode({"kw" : kw})

    # 组合后的url示例：http://tieba.baidu.com/f?kw=lol
    url = url + key
    tiebaSpider(url, beginPage, endPage)

    接下来，我们写一个百度贴吧爬虫接口，我们需要传递3个参数给这个接口，一个是main里组合url地址，以及起始页和终止页码
    ，表示要爬取页码的范围。

def tiebaSpider(url, beginPage, endPage):
    """
        作用：负责处理url，分配每个url去发送请求
        url：需要处理的第一个url
        beginPage: 爬虫执行的起始页面
        endPage: 爬虫执行的截止页面
    """


    for page in range(beginPage, endPage + 1):
        pn = (page - 1) * 50

        filename = "第" + str(page) + "页.html"
        # 组合为完整的 url，并且pn值每次增加50
        fullurl = url + "&pn=" + str(pn)
        #print fullurl

        # 调用loadPage()发送请求获取HTML页面
        html = loadPage(fullurl, filename)
        # 将获取到的HTML页面写入本地磁盘文件
        writeFile(html, filename)

    我们已经之前写出一个爬取一个网页的代码。现在，我们可以把它封装成一个loadPage,供我们使用。

def loadPage(url, filename):
    ‘‘‘
        作用：根据url发送请求，获取服务器响应文件
        url：需要爬取的url地址
        filename: 文件名
    ‘‘‘
    print "正在下载" + filename

    headers = {"User-Agent": "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"}

    request = urllib2.Request(url, headers = headers)
    response = urllib2.urlopen(request)
    return response.read()

    最后如果我们希望将爬取到了每页的信息存储在本地磁盘上，我们可以简单写一个存储文件的接口。

def writeFile(html, filename):
    """
        作用：保存服务器响应文件到本地磁盘文件里
        html: 服务器响应文件
        filename: 本地磁盘文件名
    """
    print "正在存储" + filename
    with open(filename, ‘w‘) as f:
        f.write(html)
    print "-" * 20

#-*- coding:utf-8 -*-
#09.urllib2_post.py

import urllib
import urllib2

#POST请求的目标URL
url = "http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null"

headers = {"User-Agent":"Mozilla...."}

formate = {
    "type":"AUTO",
    "i":"i love python",
    "doctype":"json",
    "xmlVersion":"1.8",
    "keyform":"fanyi.web",
    "ue":"utf-8",
    "action":"FY_BY_ENTER",
    "typoResult":"true"
}

data = urllib.urlencode(formate)

request = urllib2.Request(url, data=data, headers = headers)

response = urllib2.urlopen(request)

print("-"*30)
print(response.read())

#-*- coding:utf-8 -*-
#10.urllib2_ajax.py
import urllib
import urllib2

# demo1

url = "https://movie.douban.com/j/chart/top_list?type=11&interval_id=100%3A90&action"

headers={"User-Agent": "Mozilla...."}

# 变动的是这两个参数，从start开始往后显示limit个
formdata = {
    ‘start‘:‘0‘,
    ‘limit‘:‘10‘
}
data = urllib.urlencode(formdata)

request = urllib2.Request(url, data = data, headers = headers)
response = urllib2.urlopen(request)

print(response.read())


#demo2
url = "https://movie.douban.com/j/chart/top_list?"
headers={"User-Agent": "Mozilla...."}

# 处理所有参数
formdata = {
    ‘type‘:‘11‘,
    ‘interval_id‘:‘100:90‘,
    ‘action‘:‘‘,
    ‘start‘:‘0‘,
    ‘limit‘:‘10‘
}
data = urllib.urlencode(formdata)

request = urllib2.Request(url, data = data, headers = headers)
response = urllib2.urlopen(request)

print response.read()

<form action="form_action.asp" method="get">
    <p>First name: <input type="text" name="fname" /></p>
    <p>Last name: <input type="text" name="lname" /></p>
    <input type="submit" value="Submit" />
</form>

import urllib2

url = "https://www.12306.cn/mormhweb/"

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}

request = urllib2.Request(url, headers = headers)

response = urllib2.urlopen(request)

print(response.read())

import urllib
import urllib2
# 1. 导入Python SSL处理模块
import ssl

# 2. 表示忽略未经核实的SSL证书认证
context = ssl._create_unverified_context()

url = "https://www.12306.cn/mormhweb/"

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}

request = urllib2.Request(url, headers = headers)

# 3. 在urlopen()方法里 指明添加 context 参数
response = urllib2.urlopen(request, context = context)

print response.read()