scrpy-cookie

两种方法模拟登陆

1.直接携带cookie

import re
import scrapy

class RenrenSpider(scrapy.Spider):
    name = 'renren'
    allowed_domains = ['renren.com']
    start_urls = ['http://renren.com/']
    # 重写start_urls的处理方法，加上cookies
    def start_requests(self):
        cookies = '''anonymid=juzai6na-g0fmvf; depovince=GW; _r01_=1; ick_login=9de0dec9-4f94-42e0-819b-22df9e9adf66; ick=75ca63f4-c056-4af0-ba6e-7683bb07d04d; 
jebecookies=747a7092-f53c-40ae-bc0b-90b3f9ab5e2d|||||; JSESSIONID=abcjUmG7wh1SragUBfEPw; _de=8B28AA93122391F898B641D1F469956B; p=9984be9e31957abbf89e6751ad2fd8f48; 
first_login_flag=1; ln_uact=18781736136; ln_hurl=http://head.xiaonei.com/photos/0/0/men_main.gif; t=59071958da717542e6a80ffd0df189c38; 
societyguester=59071958da717542e6a80ffd0df189c38; id=970578188; xnsid=a1ea20ee; ver=7.0; loginfrom=null; 
jebe_key=ed626104-9dc0-45aa-961c-2cfea0e1935d%7C570ae1432b36360003bbd95b7fb6661a%7C1556356655118%7C1%7C1556356654129; 
wp_fold=0; XNESSESSIONID=2d1bc0ef1740; vip=1'''
        cookies = {i.split('=')[0]: i.split('=')[1] for i in cookies.split('; ')}
        start_urls = ['http://www.renren.com/970578188/profile?v=info_timeline']
        yield scrapy.Request(
            start_urls[0],
            callback=self.parse_detail,
            cookies=cookies
        )

    def parse_detail(self, response):
        res = response.xpath("//div[@class='love-infobox']/p/text()").extract_first()
        print(res)
        # print(re.findall(r'单身', response.body.decode()))

2.找到发送post请求的url地址，带上信息，发送请求 。  scrapy.FormRequest

# 模拟github网登陆
class Renren1Spider(scrapy.Spider):
    name = 'renren1'
    allowed_domains = ['github.com']
    start_urls = ['http://github.com/login']
    # func 1
    def parse(self, response):
        authenticity_token = response.xpath("//input[@name='authenticity_token']/@value").extract_first()
        utf8 = response.xpath("//input[@name='utf8']/@value").extract_first()
        commit = response.xpath("//input[@name='commit']/@value").extract_first()
　　　　　# 所有的form data
        post_data = dict(
            login='tangpinggui',
            password='***********',
            authenticity_token=authenticity_token,
            utf8=utf8,
            commit=commit
        )
        yield scrapy.FormRequest(
            url="https://github.com/session",
            formdata=post_data,
            callback=self.after_login
        )
    # func 2
    def parse(self, response):
　　　　　# 只需要登陆名及密码，其它form data数据由FormRequest.from_response 找到
        post_data = dict(
            login='tangpinggui',
            password='*********',
        )
        yield scrapy.FormRequest.from_response(
            response, # 自动从response找到form表单
            formdata=post_data,
            callback=self.after_login
        )

    def after_login(self, response):
        res = response.xpath("//a[@class='btn btn-outline mt-2']/text()").extract_first()
        print(res)

# 模拟人人网网登陆
class Renren1Spider(scrapy.Spider):
    name = 'renren1'
    allowed_domains = ['renren.com']
    start_urls = ['http://renren.com']
    """
    email: 18781736136
    icode:
    origURL: http://www.renren.com/970578188/profile?v=info_timeline
    domain: renren.com
    key_id: 1
    captcha_type: web_login
    password: 6af626fe325aa7fcea5e6ff3c541404d9104667d6d941a5c5c30390c2d5da8ad
    rkey: 86cfb8063d4b47d05407cc549819f975
    f:
    """
    # func 1
    def parse(self, response):
        origURL = response.xpath("//input[@name='origURL']/@value").extract_first()
        domain = 'renren.com'
        key_id = response.xpath("//input[@name='key_id']/@value").extract_first()
        captcha_type = response.xpath("//input[@name='captcha_type']/@value").extract_first()
        # rkey = response.xpath("//input[@name='rkey']/@value").extract_first()
        post_data = dict(
            email='1********',
            password='**********',
            origURL=origURL,
            domain=domain,
            key_id=key_id,
            captcha_type=captcha_type,
            # rkey='', #不知道怎么获取,貌似不要也能登录
            f=''
        )
        yield scrapy.FormRequest(
            url="http://www.renren.com/PLogin.do",
            formdata=post_data,
            callback=self.after_login
        )
    # func 2
    def parse(self, response):
        post_data = dict(
            email='1********',
            password='**************',
        )
        yield scrapy.FormRequest.from_response(
            response, # 自动从response找到form表单中
            formdata=post_data,
            callback=self.after_login
        )

    def after_login(self, response):
        print('start....')
        with open('renren.html', 'w') as f:
            f.write(response.body.decode())