我修改了一个网络抓取模板，用于满足我的大多数基于 Python 的抓取需求，以满足您的需求。验证它与我自己的登录信息一起使用。
它的工作方式是模仿浏览器并维护一个 cookieJar 来存储您的用户会话。让它与 BeautifulSoup 一起为你工作。
注意：这是 Python2 版本。我应要求在下面进一步添加了一个工作 Python3 示例。
import cookielib
import os
import urllib
import urllib2
import re
import string
from BeautifulSoup import BeautifulSoup
username = "user@email.com"
password = "password"
cookie_filename = "parser.cookies.txt"
class LinkedInParser(object):
def __init__(self, login, password):
""" Start up... """
self.login = login
self.password = password
# Simulate browser with cookies enabled
self.cj = cookielib.MozillaCookieJar(cookie_filename)
if os.access(cookie_filename, os.F_OK):
self.cj.load()
self.opener = urllib2.build_opener(
urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0),
urllib2.HTTPCookieProcessor(self.cj)
)
self.opener.addheaders = [
('User-agent', ('Mozilla/4.0 (compatible; MSIE 6.0; '
'Windows NT 5.2; .NET CLR 1.1.4322)'))
]
# Login
self.loginPage()
title = self.loadTitle()
print title
self.cj.save()
def loadPage(self, url, data=None):
"""
Utility function to load HTML from URLs for us with hack to continue despite 404
"""
# We'll print the url in case of infinite loop
# print "Loading URL: %s" % url
try:
if data is not None:
response = self.opener.open(url, data)
else:
response = self.opener.open(url)
return ''.join(response.readlines())
except:
# If URL doesn't load for ANY reason, try again...
# Quick and dirty solution for 404 returns because of network problems
# However, this could infinite loop if there's an actual problem
return self.loadPage(url, data)
def loginPage(self):
"""
Handle login. This should populate our cookie jar.
"""
html = self.loadPage("https://www.linkedin.com/")
soup = BeautifulSoup(html)
csrf = soup.find(id="loginCsrfParam-login")['value']
login_data = urllib.urlencode({
'session_key': self.login,
'session_password': self.password,
'loginCsrfParam': csrf,
})
html = self.loadPage("https://www.linkedin.com/uas/login-submit", login_data)
return
def loadTitle(self):
html = self.loadPage("https://www.linkedin.com/feed/")
soup = BeautifulSoup(html)
return soup.find("title")
parser = LinkedInParser(username, password)
2014 年 6 月 19 日更新：添加了从主页解析 CSRF 令牌以用于更新的登录过程。
2015 年 7 月 23 日更新：在此处添加 Python 3 示例。基本上需要替换库位置并删除不推荐使用的方法。它没有完美的格式或任何东西，但它可以工作。很抱歉赶工。最后，原则和步骤是相同的。
import http.cookiejar as cookielib
import os
import urllib
import re
import string
from bs4 import BeautifulSoup
username = "user@email.com"
password = "password"
cookie_filename = "parser.cookies.txt"
class LinkedInParser(object):
def __init__(self, login, password):
""" Start up... """
self.login = login
self.password = password
# Simulate browser with cookies enabled
self.cj = cookielib.MozillaCookieJar(cookie_filename)
if os.access(cookie_filename, os.F_OK):
self.cj.load()
self.opener = urllib.request.build_opener(
urllib.request.HTTPRedirectHandler(),
urllib.request.HTTPHandler(debuglevel=0),
urllib.request.HTTPSHandler(debuglevel=0),
urllib.request.HTTPCookieProcessor(self.cj)
)
self.opener.addheaders = [
('User-agent', ('Mozilla/4.0 (compatible; MSIE 6.0; '
'Windows NT 5.2; .NET CLR 1.1.4322)'))
]
# Login
self.loginPage()
title = self.loadTitle()
print(title)
self.cj.save()
def loadPage(self, url, data=None):
"""
Utility function to load HTML from URLs for us with hack to continue despite 404
"""
# We'll print the url in case of infinite loop
# print "Loading URL: %s" % url
try:
if data is not None:
response = self.opener.open(url, data)
else:
response = self.opener.open(url)
return ''.join([str(l) for l in response.readlines()])
except Exception as e:
# If URL doesn't load for ANY reason, try again...
# Quick and dirty solution for 404 returns because of network problems
# However, this could infinite loop if there's an actual problem
return self.loadPage(url, data)
def loadSoup(self, url, data=None):
"""
Combine loading of URL, HTML, and parsing with BeautifulSoup
"""
html = self.loadPage(url, data)
soup = BeautifulSoup(html, "html5lib")
return soup
def loginPage(self):
"""
Handle login. This should populate our cookie jar.
"""
soup = self.loadSoup("https://www.linkedin.com/")
csrf = soup.find(id="loginCsrfParam-login")['value']
login_data = urllib.parse.urlencode({
'session_key': self.login,
'session_password': self.password,
'loginCsrfParam': csrf,
}).encode('utf8')
self.loadPage("https://www.linkedin.com/uas/login-submit", login_data)
return
def loadTitle(self):
soup = self.loadSoup("https://www.linkedin.com/feed/")
return soup.find("title")
parser = LinkedInParser(username, password)