相关疑难解决方法(0)

无法解析用户名以确保我已登录网站

我已经用 python 编写了一个脚本来登录网站并解析用户名以确保我真的能够登录。使用我在下面尝试过的方式似乎可以让我到达那里。但是,我在脚本中使用了从 chrome 开发工具中获取的硬编码 cookie 来获得成功。

我试过:

import requests
from bs4 import BeautifulSoup

url = 'https://secure.imdb.com/ap/signin?openid.pape.max_auth_age=0&openid.return_to=https%3A%2F%2Fwww.imdb.com%2Fap-signin-handler&openid.identity=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&openid.assoc_handle=imdb_pro_us&openid.mode=checkid_setup&siteState=eyJvcGVuaWQuYXNzb2NfaGFuZGxlIjoiaW1kYl9wcm9fdXMiLCJyZWRpcmVjdFRvIjoiaHR0cHM6Ly9wcm8uaW1kYi5jb20vIn0&openid.claimed_id=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0%2Fidentifier_select&openid.ns=http%3A%2F%2Fspecs.openid.net%2Fauth%2F2.0'
signin = 'https://secure.imdb.com/ap/signin'
mainurl = 'https://pro.imdb.com/'

with requests.Session() as s:
    res = s.get(url,headers={"User-agent":"Mozilla/5.0"})
    soup = BeautifulSoup(res.text,"lxml")
    payload = {i['name']: i.get('value', '') for i in soup.select('input[name]')}
    payload['email'] = 'some username'
    payload['password'] = 'some password'

    s.post(signin,data=payload,headers={
        "User-agent":"Mozilla/5.0",
        "Cookie": 'adblk=adblk_yes; ubid-main=130-2884709-6520735; _msuuid_518k2z41603=95C56F3B-E3C1-40E5-A47B-C4F7BAF2FF5D; _fbp=fb.1.1574621403438.97041399; pa=BCYm5GYAag-hj1CWg3cPXjfv2X6NGPUp6kLguepMku7Yf0W9-iSTjgmVNGmQLwUfJ5XJPHqlh84f%0D%0Agrd2voq0Q7TR_rdXU4T1BJw-1a-DdvCNSVuWSm50IXJDC_H4-wM_Qli_%0D%0A; uu=BCYnANeBBdnuTg3UKEVGDiO203C7KR0AQTdyE9Y_Y70vpd04N5QZ2bD3RwWdMBNMAJtdbRbPZMpG%0D%0AbPpC6vZvoMDzucwsE7pTQiKxY24Gr4_-0ONm7hGKPfPbMwvI1NYzy5ZhTIyIUqeVAQ7geCBiS5NS%0D%0A1A%0D%0A; session-id=137-0235974-9052660; session-id-time=2205351554; session-token=jsvzgJ4JY/TCgodelKegvXcqdLyAy4NTDO5/iEvk90VA8qWWEPJpiiRYAZe3V0EYVFlKq590mXU0OU9XMbAzwyKqXIzPLzKfLf3Cc3k0g/VQNTo6roAEa5IxmOGZjWrJuhkRZ1YgeF5uPZLcatWF1y5PFHqvjaDxQrf2LZbgRXF5N7vacTZ8maK0ciJmQEjh; csm-hit=tb:8HH0DWNBDVSWP881GYKG+s-8HH0DWNBDVSWP881GYKG|1574631571950&t:1574631571952&adb:adblk_yes'
        })

    r = s.get(mainurl,headers={
        "Cookie": 'adblk=adblk_yes; ubid-main=130-2884709-6520735; _msuuid_518k2z41603=95C56F3B-E3C1-40E5-A47B-C4F7BAF2FF5D; _fbp=fb.1.1574621403438.97041399; pa=BCYm5GYAag-hj1CWg3cPXjfv2X6NGPUp6kLguepMku7Yf0W9-iSTjgmVNGmQLwUfJ5XJPHqlh84f%0D%0Agrd2voq0Q7TR_rdXU4T1BJw-1a-DdvCNSVuWSm50IXJDC_H4-wM_Qli_%0D%0A; csm-hit=tb:KV47B1QVKP4DNB3QGY95+b-NM69W1Y35R7ARV0639V5|1574631544432&t:1574631544432&adb:adblk_yes; session-id=137-0235974-9052660; session-id-time=2205351554; session-token="EsIzROiSTmFDfXd5jnBPIBOpYG9jAu7tiWXDF8R52sUw5jS6OjddfOOQB+ytCmq0K3UnXs9wKBvQtkB4aVNsXieVbRcIUrKf3iPnYeJchbOlShMjg+MR+O7IQgPKkw0BKihdYQ1YIl7KQS8VeLxZjtzJ5sj5ocnY72fCKdwq/fGOjfieFYbe9Km3a8h++1GpC738JbwcVdpTG08v1pjhQKifqPQXnqhcyVKhi8CD1qk="; x-main="C1KbtQgFFBAYfwttdRSrU5CpCe@Fn6SPHnBTY6dO2ppimt@u1P1L7G0PueQMn6X3"; at-main=Atza|IwEBICfS3UKNp2mwmbyUPY1QzjXRHMcL6fjv2ND7BDXsZ1G-qDPJKsLJXeU9gJOvRpWsofSpOJCyhnap-bIOWCutU6VMIS9bn3UkNVRP8WFVqrs-CLB5opLbrEx6YxVGQlfaxx54gzuuGO4D30z-AgBpGe64_bn0K1iLOT3P3i7S3nBzvP_0AopwKlbU7SRnE5m21cVfVK7bwbtfZO4cf7DrpGcaHK4dlY5jKHPzNx_AR4ypqsEBFbHon36N1j8foty6wLJhFP1gNCvs24mVCec24TRho5ZXFDYqhLB-dw9V3XY1eq7q1QNgtAdYkDSJ6Mq1nllFu59WqIVs1Y3lLEaxDUExLtCt-VQArpS_hZtZR8C_kevhV01jEhWg8RUQaCdYTMwZHwa778MiEOrrrdGqFnR5; sess-at-main="tWwUfkZLx+mDAPqZo+J6yJlnjqBJvYJ0oVMS6/NcIKQ="; …
Run Code Online (Sandbox Code Playgroud)

python web-scraping python-3.x

9
推荐指数
1
解决办法
748
查看次数

标签 统计

python ×1

python-3.x ×1

web-scraping ×1