爬虫学习 -- day4

# -*- coding: utf-8 -*-
import json

import scrapy

from zhihuuser.items import ZhihuItem


class ZhihuSpider(scrapy.Spider):
    name = 'zhihu'
    allowed_domains = ['www.zhihu.com']
    start_urls = ['http://www.zhihu.com/']
    user_url = 'https://www.zhihu.com/api/v4/members/{user}?include={include}'
    follows_url = 'https://www.zhihu.com/api/v4/members/{user}/followees?include={include}&offset={offset}&limit={limit}'
    start_user = 'excited-vczh'
    users_qurey = 'allow_message%2Cis_followed%2Cis_following%2Cis_org%2Cis_blocking%2Cemployments%2Canswer_count%2Cfollower_count%2Carticles_count%2Cgender%2Cbadge%5B%3F(type%3Dbest_answerer)%5D.topics'
    follows_qurey ='data[*].answer_count,articles_count,gender,follower_count,is_followed,is_following,badge[?(type=best_answerer)].topics'

    def start_requests(self):
        yield scrapy.Request(self.user_url.format(user=self.start_user,include=self.users_qurey),self.parse_user)
        yield scrapy.Request(self.follows_url.format(user=self.start_user,include=self.follows_qurey,limit=20,offset=0),self.parse_follows)

    def parse_user(self, response):
        result = json.loads(response.text)
        item = ZhihuItem()

        for field in item.fields:
            if field in result.keys():
                item[field] = result.get(field)
        yield item

    def parse_follows(self, response):
        results = json.loads(response.text)

        if 'data' in results.keys():
            for result in results.get('data'):
                yield scrapy.Request(self.user_url.format(user=result.get('url_token'), include=self.users_qurey),self.parse_user)

        if 'paging' in results.keys() and results.get('paging').get('is_end') == False:
            next_page = results.get('paging').get('next')
            yield scrapy.Request(next_page,self.parse_follows)