如何抓取需要首先使用Python登录的网站

Question

首先，我认为值得一提，我知道有很多类似的问题，但是没有一个对我有用。

我是Python，html和网络抓取工具的新手。我正在尝试从需要先登录的网站上抓取用户信息。在我的测试中，我以来自github的scraper我的电子邮件设置为例。主页是“
https://github.com/login ”，目标页面是“
https://github.com/settings/emails ”

这是我尝试过的方法列表

##################################### Method 1
import mechanize
import cookielib
from BeautifulSoup import BeautifulSoup
import html2text

br = mechanize.Browser()
cj = cookielib.LWPCookieJar()
br.set_cookiejar(cj)

# Browser options
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', 'Chrome')]

# The site we will navigate into, handling it's session
br.open('https://github.com/login')

for f in br.forms():
    print f

br.select_form(nr=0)

# User credentials
br.form['login'] = 'myusername'
br.form['password'] = 'mypwd'

# Login
br.submit()

br.open('github.com/settings/emails').read()


################ Method 2
import urllib, urllib2, cookielib

username = 'myusername'
password = 'mypwd'

cj = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
login_data = urllib.urlencode({'username' : username, 'j_password' : password})
opener.open('https://github.com/login', login_data)
resp = opener.open('https://github.com/settings/emails')
print resp.read()



############# Method 3
import urllib
opener = urllib.FancyURLopener()
print opener.open('http://myusername:[e-mail]/settings/emails').read()




########## Method 4
import mechanize
import cookielib

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.set_debug_http(True)
#br.set_debug_redirects(True)
#br.set_debug_responses(True)

br.addheaders = [('User-agent', 'Chrome')]

br.add_password('https://github.com/settings/emails', 'myusername', 'mypwd')
br.open('https://github.com/settings/emails')
print br.response().read()



############ Methods 5
from requests import session

payload = {
    'action': 'login',
    'username': 'myusername',
    'password': 'mypwd'
}

with session() as c:
    c.post('https://github.com/login', data=payload)
    request = c.get('https://github.com/settings/emails')
    print request.headers
    print request.text



########### Method 6
import requests
from requests.packages.urllib3 import add_stderr_logger
import sys
from bs4 import BeautifulSoup as bs

add_stderr_logger()
s = requests.Session()

s.headers['User-Agent'] = 'Chrome'

username = 'myusername'
password = 'mypwd'
url = 'https://github.com/login'

# after examining the HTML of the website you're trying to log into
# set name_form to the name of the form element that contains the name and
# set password_form to the name of the form element that will contain the password
login = {'login': username, 'password': password}
login_response = s.post(url, data=login)
for r in login_response.history:
    if r.status_code == 401:  # 401 means authentication failed
        print 'error!'
        sys.exit(1)  # abort


pdf_response = s.get('https://github.com/settings/emails')  # Your cookies and headers are automatically included
soup = bs(pdf_response.content)

我也阅读了一些有关HTTP身份验证和cookie之间差异的讨论。仍然没有一个工作。

请帮助，任何帮助将不胜感激。非常感谢你。

Answer 1

这对我有用：

##################################### Method 1
import mechanize
import cookielib
from BeautifulSoup import BeautifulSoup
import html2text

# Browser
br = mechanize.Browser()

# Cookie Jar
cj = cookielib.LWPCookieJar()
br.set_cookiejar(cj)

# Browser options
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', 'Chrome')]

# The site we will navigate into, handling it's session
br.open('https://github.com/login')

# View available forms
for f in br.forms():
    print f

# Select the second (index one) form (the first form is a search query box)
br.select_form(nr=1)

# User credentials
br.form['login'] = 'mylogin'
br.form['password'] = 'mypass'

# Login
br.submit()

print(br.open('https://github.com/settings/emails').read())

你一点也不远！