如何从ubuntu服务器以编程方式登录到Yahoo

Question

我想从ubuntu服务器上运行的脚本登录我的yahoo帐户.我曾试图将python与机械化一起使用,但我的计划存在缺陷.

这是我目前的代码.

        loginurl = "https://login.yahoo.com/config/login"
        br = mechanize.Browser()
        cj = cookielib.LWPCookieJar()
        br.set_cookiejar(cj)
        br.set_handle_equiv(True)
        br.set_handle_gzip(True)
        br.set_handle_redirect(True)
        br.set_handle_referer(True)
        br.set_handle_robots(False)
        br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)
        br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
        r = br.open(loginurl)
        html = r.read()
        br.select_form(nr=0)
        br.form['login']='[mylogin]'
        br.form['passwd']='[mypassword]'
        br.submit()

        print br.response().read()

我得到的回复是雅虎登录页面,带有醒目的红色文本阅读."必须在你的broswer上启用Javascript"或类似的东西.机械化文档中有一节提到用JS创建cookie的页面,但是帮助页面返回HTTP 400(只是我的运气)

弄清楚javascript的功能,然后手动执行它听起来像是一项非常困难的任务.我愿意切换到任何工具/语言,只要它可以在ubuntu服务器上运行.即使这意味着使用不同的工具进行登录,然后将登录cookie传递回我的python脚本.任何帮助/建议表示赞赏.

更新:

• 我不想使用Yahoo API

• 我也尝试过scrapy,但我认为同样的问题也会发生

我的scrapy脚本

class YahooSpider(BaseSpider):
name = "yahoo"
start_urls = [
    "https://login.yahoo.com/config/login?.intl=us&.lang=en-US&.partner=&.last=&.src=&.pd=_ver%3D0%26c%3D%26ivt%3D%26sg%3D&pkg=&stepid=&.done=http%3a//my.yahoo.com"
]

def parse(self, response):
    x = HtmlXPathSelector(response)
    print x.select("//input/@value").extract()
    return [FormRequest.from_response(response,
                formdata={'login': '[my username]', 'passwd': '[mypassword]'},
                callback=self.after_login)]

def after_login(self, response):
    # check login succeed before going on
    if response.url == 'http://my.yahoo.com':
        return Request("[where i want to go next]",
                  callback=self.next_page, errback=self.error, dont_filter=True)
    else:
        print response.url
        self.log("Login failed.", level=log.CRITICAL)

def next_page(sekf, response):
    x = HtmlXPathSelector(response)
    print x.select("//title/text()").extract()

scrapy脚本只输出"https://login.yahoo.com/config/login"...... boo

Answer 1

我很惊讶这有效：

Python 2.6.6 (r266:84292, Dec 26 2010, 22:31:48)
[GCC 4.4.5] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> from BeautifulSoup import BeautifulSoup as BS
>>> import requests
>>> r = requests.get('https://login.yahoo.com/')
>>> soup = BS(r.text)
>>> login_form = soup.find('form', attrs={'name':'login_form'})
>>> hiddens = login_form.findAll('input', attrs={'type':'hidden'})
>>> payload = {}
>>> for h in hiddens:
...     payload[str(h.get('name'))] = str(h.get('value'))
...
>>> payload['login'] = 'testtest481@yahoo.com'
>>> payload['passwd'] = '********'
>>> post_url = str(login_form.get('action'))
>>> r2 = requests.post(post_url, cookies=r.cookies, data=payload)
>>> r3 = requests.get('http://my.yahoo.com', cookies=r2.cookies)
>>> page = r3.text
>>> pos = page.find('testtest481')
>>> print page[ pos - 50 : pos + 300 ]
   You are signed in as: <span class="yuhead-yid">testtest481</span>        </li>    </ul></li><li id="yuhead-me-signout" class="yuhead-me"><a href="
http://login.yahoo.com/config/login?logout=1&.direct=2&.done=http://www.yahoo.com&amp;.src=my&amp;.intl=us&amp;.lang=en-US" target="_top" rel="nofoll
ow">            Sign Out        </a><img width='0' h
>>>

请尝试一下：

"""                                                                        
ylogin.py - how-to-login-to-yahoo-programatically-from-an-ubuntu-server    

http://stackoverflow.com/questions/11974478/                               
Test my.yahoo.com login using requests and BeautifulSoup.                  
"""                                                                        

from BeautifulSoup import BeautifulSoup as BS                              
import requests                                                            

CREDS = {'login': 'CHANGE ME',                                             
         'passwd': 'CHANGE ME'}                                            
URLS = {'login': 'https://login.yahoo.com/',                               
        'post': 'https://login.yahoo.com/config/login?',                   
        'home': 'http://my.yahoo.com/'}                                    

def test():                                                                
    cookies = get_logged_in_cookies()                                      
    req_with_logged_in_cookies = requests.get(URLS['home'], cookies=cookies)    
    assert 'You are signed in' in req_with_logged_in_cookies.text
    print "If you can see this message you must be logged in." 

def get_logged_in_cookies():                                               
    req = requests.get(URLS['login'])                                      
    hidden_inputs = BS(req.text).find('form', attrs={'name':'login_form'})\
                                .findAll('input', attrs={'type':'hidden'}) 
    data = dict(CREDS.items() + dict( (h.get('name'), h.get('value')) \    
                                         for h in hidden_inputs).items() ) 
    post_req = requests.post(URLS['post'], cookies=req.cookies, data=data) 
    return post_req.cookies                                                

test()                                                                     

根据需要添加错误处理。