import scrapy


class LoginSpider(scrapy.Spider):
    name = 'login'
    start_urls = ['https://github.com/login']

    def parse(self, response):
        ever_token = response.xpath('//*[@id="login"]/div[4]/form/input[1]/@value').extract_first()
        timestamp_secret = response.xpath('//*[@id="login"]/div[4]/form/div/input[11]/@value').extract_first()
        timestamp = response.xpath('//*[@id="login"]/div[4]/form/div/input[10]/@value').extract_first()

        data = {
            "commit": "Sign in",
            "authenticity_token": ever_token, # token每次都会变,可以在login网页中查找到
            "login": "xxx", # 填成自己的
            "password": "xxx", # 填成自己的
            "webauthn-support": "supported",
            "webauthn-iuvpaa-support": "unsupported",
            "return_to": "https://github.com/login",
            "timestamp": timestamp,
            "timestamp_secret": timestamp_secret
        }

        yield scrapy.FormRequest(  # 用的就是post方式
            url='https://github.com/session', # post网址
            callback=self.after_login,
            formdata=data
        )

    def after_login(self, response):
        yield scrapy.Request('https://github.com/yezhoubing', callback=self.check_login)

    def check_login(self, response):
        print(response.xpath('html/head/title/text()').extract_first())

def __init__(self):
       self.bro = Chrome() # 默认路径为python.exe所在文件夹

"""scrapy异步下载图片"""

import scrapy
from selenium.webdriver import Chrome
from ..items import ServantPicItem
import pandas as pd
import numpy as np
from scrapy.pipelines.images import ImagesPipeline
class ServantSpider(scrapy.Spider):
    name_list = []
    img_list = []
    name = 'servant'
    start_urls = ['https://fgo.wiki/w/%E8%8B%B1%E7%81%B5%E5%9B%BE%E9%89%B4']



    def parse(self, response):
        item = ServantPicItem()
      

        # 读取本地csv文件
        data = pd.read_csv("link.csv",usecols=["图片名称"])
        data_array1 = np.array(data.stack())  # 首先将pandas读取的数据转化为array
        self.name_list = data_array1.tolist()
        data = pd.read_csv("link.csv",usecols=["图片链接"])
        data_array2 = np.array(data.stack())  # 首先将pandas读取的数据转化为array
        self.img_list = data_array2.tolist()  # 然后转化为list形式
        # item['name'] = self.name_list
        item['image_urls'] = self.img_list # 必须是img_urls,这是图片下载文件中有的
        yield item