import scrapy
import re
import json


class ZhihuSpider(scrapy.Spider):
    name = 'zhihu'
    allowed_domains = ['www.zhihu.com']
    start_urls = ['https://www.zhihu.com/']

    headers = {
        'HOST': 'www.zhihu.com',
        'Referer': 'https://www.zhihu.com',
        'User-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/603.3.8 (KHTML, like Gecko) Version/10.1.2 Safari/603.3.8
 
',
    }

    def parse(self, response):
        pass

    def parse_detail(self, response):
        # 爬取文章細節
        pass

    # scrapy開始時先進入start_requests()
    def start_requests(self):
        # 為了提取_xsrf：要先訪問知乎的登入頁面，讓scrapy在登入頁面獲取伺服器給我們的資料(_xsrf)，再呼叫login
        return [scrapy.Request('https://www.zhihu.com/#signin
 
', headers=self.headers, callback=self.login)]

    def login(self, response):
        xsrf = ''
        match_obj = re.match('[\s\S]*name="_xsrf" value="(.*?)"', response.text)
        if match_obj:
            xsrf =  match_obj.group(1)

        # 如果提取到了xsrf就進行下面的操作，如果沒xsrf有就沒必要往下做了
        if xsrf:
            post_data 
 
= {
                'captcha_type': 'cn',
                '_xsrf': xsrf,
                'phone_num': '13043330319',
                'password': 'Wcw19961223',
                'captcha': '',
            }
            import time
            captcha_url = 'https://www.zhihu.com/captcha.gif?r=%d&type=login&lang=cn' % (int(time.time() * 1000))
            # scrapy會預設把Request的cookie放進去
            return scrapy.Request(captcha_url, headers=self.headers, meta={'post_data': post_data}, callback=self.login_after_captcha)

    def login_after_captcha(self, response):
        # 儲存並開啟驗證碼
        with open('captcha.gif', 'wb') as f:
            f.write(response.body)
            f.close()
        from PIL import Image
        try:
            img = Image.open('captcha.gif')
            img.show()
        except:
            pass
        # 輸入驗證碼
        captcha = {
            'img_size': [200, 44],
            'input_points': [],
        }
        points = [[22.796875, 22], [42.796875, 22], [63.796875, 21], [84.796875, 20], [107.796875, 20],
                  [129.796875, 22], [150.796875, 22]]
        seq = input('請輸入倒立字的位置\n>')
        for i in seq:
            captcha['input_points'].append(points[int(i) - 1])
        captcha = json.dumps(captcha)

        post_url = 'https://www.zhihu.com/login/phone_num'
        post_data = response.meta.get('post_data', {})
        post_data['captcha'] = captcha
        return [scrapy.FormRequest(
            # 在這裡完成像之前的requests的登入操作，每一個Request如果要做下一步處理都要設定callback
            url=post_url,
            formdata=post_data,
            headers=self.headers,
            callback=self.check_login,
        )]

    def check_login(self, response):
        # 驗證伺服器的返回資料判斷是否成功
        text_json = json.loads(response.text)
        if 'msg' in text_json and text_json['msg'] == '登入成功':
            print('登入成功！')
            for url in self.start_urls:
                yield scrapy.Request(url, dont_filter=True, headers=self.headers)