Python 爬虫 (二)

cookiejar模块:

• 管理储存cookie，将传出的http请求添加cookie
• cookie存储在内存中，CookieJar示例回收后cookie将自动消失

实例:用cookjar访问人人网主页

 import json
 from urllib import request,parse
 from http import cookiejar

 #实例化一个cookiejar对象
 cookiejar_object = cookiejar.CookieJar()
 #生成cookie管理器
 cookie_handler = request.HTTPCookieProcessor(cookiejar_object)
 #有了opener,就可以代替urlopen来进行请求网页
 opener = request.build_opener(cookie_handler)

 #获取网页的登陆接口
 url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2018721532875'

 #将网页的form信息获取
 form = {
     'email':'xxx',
     'icode':'',
     'origURL':'http://www.renren.com/home',
     'domain':'renren.com',
     'key_id':'',
     'captcha_type':'web_login',
     'password':'xxx',
     'rkey':'79d8184f25d678248262a91caf3e7ea8',
     'f':'http%3A%2F%2Fzhibo.renren.com%2Ftop',
 }

 #将数据转换成二进制
 form_b = parse.urlencode(form).encode('utf-8')

 #将url和表单信息,还有获取到的cookie去访问网页
 response = opener.open(url,form_b)
 html_b = response.read()#字节类型
 # print(html_b)

 res_dict = json.loads(html_b.decode('utf-8'))
 #获取登陆后的个人主页url
 home_url = res_dict['homeUrl']

 # print(home_url)
 # 访问个人主页
 response = opener.open(home_url)
 html_bytes = response.read()
 print(html_bytes.decode('utf-8'))

python Proxy代理

 from urllib import request

 proxy = {
     'http': 'http://219.141.153.41:80'
 }

 url = 'http://www.baidu.com/s?wd=ip'
 # request.HTTPCookieProcessor(cookie)
 handler = request.ProxyHandler(proxy)

 # 生成 opener.open = urlopen
 opener = request.build_opener(handler)

 # 同过opener访问百度

 response = opener.open(url, timeout=5)
 # 存储页面
 with open('baidu.html', 'wb') as f:
     f.write(response.read())

有道词典翻译接口

 import time
 import random
 import json
 from Day1.tuozhan_all import post

 def md5_my(need_str):
     import hashlib
     # 创建md5对象
     md5_o = hashlib.md5()
     # 需要有bytes, 作为参数
     # 由str, 转换成 bytes encode-------str.encode('utf-8')
     # 由bytes转换成 str, decode---------bytes.decode('utf-8')
     sign_bytes = need_str.encode('utf-8')
     # 更新md5 object的值
     md5_o.update(sign_bytes)
     sign_str = md5_o.hexdigest()
     return sign_str

 # url

 def translate(kw):
     url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'

     headers = {
         'Accept': 'application/json, text/javascript, */*; q=0.01',
         'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
         'Connection': 'keep-alive',
         'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
         'Cookie': 'OUTFOX_SEARCH_USER_ID=-493176930@10.168.8.63; OUTFOX_SEARCH_USER_ID_NCOO=38624120.26076847; SESSION_FROM_COOKIE=unknown; JSESSIONID=aaabYcV4ZOU-JbQUha2uw; ___rl__test__cookies=1534210912076',
         'Host': 'fanyi.youdao.com',
         'Origin': 'http://fanyi.youdao.com',
         'Referer': 'http://fanyi.youdao.com/',
         'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
         'X-Requested-With': 'XMLHttpRequest',
     }

     # form 的生成1. i 需要确定, 2, salt, 3, sign
     key= kw

     # salt : ((new Date).getTime() + parseInt(10 * Math.random(), 10))
     salt = int(time.time()*1000 + random.randint(0,10))
     print('salt:',salt)
     salt_str = str(salt)

     # sign : o = u.md5(S + n + r + D);
     # S = "fanyideskweb"
     # D = "ebSeFb%=XZ%T[KZ)c(sy!"
     # n = key
     # r = salt_str
     S = "fanyideskweb"
     D = "ebSeFb%=XZ%T[KZ)c(sy!"
     sign_str = S + key + salt_str + D
     # md5 加密的方法
     sign_md5_str = md5_my(sign_str)

     form = {
         'i': key,
         'from': 'AUTO',
         'to': 'AUTO',
         'smartresult': 'dict',
         'client': 'fanyideskweb',
         'salt': salt_str,
         'sign': sign_md5_str,
         'doctype': 'json',
         'version': '2.1',
         'keyfrom': 'fanyi.web',
         'action': 'FY_BY_REALTIME',
         'typoResult': 'false',
     }

     html_bytes = post(url, form, headers=headers)

     # 将 json 类型的 str, 转化成, 字典
     res_dict = json.loads(html_bytes.decode('utf-8'))
     #print(html_bytes.decode('utf-8'))

     translate_res = res_dict['translateResult'][0][0]['tgt']
     return translate_res

 if __name__ == '__main__':
     ret = translate('中国')

     print('翻译的结果:' + ret)