Question

我正在尝试使用Scrapy登录到init中的网站，然后在确认登录后我想初始化并通过start_urls启动标准爬网。我不知道出了什么问题，但我清楚登录并且每件事都确认，但parse_item永远不会启动。任何帮助都将受到赞赏。

我可以说到“================成功登录=================”

但

我无法进入“========================== PARSE ITEM ============= =============“

from scrapy.contrib.spiders.init import InitSpider
from scrapy.http import Request, FormRequest
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.spiders import Rule
from selenium import webdriver

class ProductDetailsSpider(InitSpider):
    name = 'product_details_spider'
    allowed_domains = ['my_domain.com']
    login_page = 'http://www.my_domain.com/'
    start_urls = ['http://www.my_domain.com/nextpage1/',
                  'http://www.my_domain.com/nextpage2/',
                  'http://www.my_domain.com/nextpage3/']

    rules = (
        Rule(SgmlLinkExtractor(allow=()),
            callback='parse_item',
            follow=True),
        )

    def get_cookies(self):
        driver = webdriver.Firefox()
        driver.implicitly_wait(30)
        base_url = "http://www.my_domain.com"
        driver.get(base_url + "/")
        driver.find_element_by_name("USR").clear()
        driver.find_element_by_name("USR").send_keys("my_user")
        driver.find_element_by_name("PASSWRD").clear()
        driver.find_element_by_name("PASSWRD").send_keys("my_pass")
        driver.find_element_by_name("submit").click()
        cookies = driver.get_cookies()
        driver.close()
        cookie_dic = {}
        for c in cookies:
            cookie_dic[c['name']] = c['value']
        return cookie_dic

    def init_request(self):
        print '=======================INIT======================='
        """This function is called before crawling starts."""
        return Request(url=self.login_page, callback=self.login)

    def login(self, response):
        print '=======================LOGIN======================='
        """Generate a login request."""
        return [FormRequest.from_response(response,formname='login_form',
            formdata={'USR': 'my_user', 'PASSWRD': 'my_pass'},
            callback=self.login_cookies)]

    def login_cookies(self, response):
        print '=======================COOKIES======================='
        return Request(url='http://www.my_domain.com/home',
            cookies=self.get_cookies(),
            callback=self.check_login_response)

    def check_login_response(self, response):
        print '=======================CHECK LOGIN======================='
        """Check the response returned by a login request to see if we are
        successfully logged in.
        """
        if "Logoff" in response.body:
            print "=========Successfully logged in.========="
            self.initialized()
            # Now the crawling can begin..
        else:
            print "==============Bad times :(==============="
            # Something went wrong, we couldn't log in, so nothing happens.

    def parse_item(self, response):
        print "==============PARSE ITEM=========================="
    # Scrape data from page

Answer 1

我参加聚会有点晚了，但我很确定你需要返回self.intialized（）：

if "Logoff" in response.body:
    print "=========Successfully logged in.========="
    return self.initialized()
    # Now the crawling can begin..

Scrapy InIt self.initialized（） - 没有初始化

1 个答案: