我用Python爬了7W知乎用户信息，终于捕获了心仪小姐姐......

$ scrapy startproject zhihuxjj

关注者列表链接构成：'https://www.zhihu.com/api/v4/members/' + '用户id' + '/followees?include=data[*].answer_count,articles_count,gender,follower_count,is_followed,is_following,badge[?(type=best_answerer)].topics&offset=0&limit=20'
个人信息链接构成：'https://www.zhihu.com/api/v4/members/' + '用户id' + '?include=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'

import json
from zhihuxjj.items import ZhihuxjjItem
from scrapy import Spider,Request

class ZhihuxjjSpider(Spider):
    name='zhihuxjj' #scrapy用于区别其他spider的名字，具有唯一性。
    allowed_domains = ["www.zhihu.com"] #爬取范围
    start_urls = ["https://www.zhihu.com/"]
    start_user = "jixin"
    followees_url = 'https://www.zhihu.com/api/v4/members/{user}/followees?include=data[*].answer_count,articles_count,gender,follower_count,is_followed,is_following,badge[?(type=best_answerer)].topics&offset={offset}&limit=20' #关注列表网址
    user_url = 'https://www.zhihu.com/api/v4/members/{user}?include=locations,employments,gender,educations,business,voteup_count,thanked_Count,follower_count,following_count,cover_url,following_topic_count,following_question_count,following_favlists_count,following_columns_count,avatar_hue,answer_count,articles_count,pins_count,question_count,commercial_question_count,favorite_count,favorited_count,logs_count,marked_answers_count,marked_answers_text,message_thread_token,account_status,is_active,is_force_renamed,is_bind_sina,sina_weibo_url,sina_weibo_name,show_sina_weibo,is_blocking,is_blocked,is_following,is_followed,mutual_followees_count,vote_to_count,vote_from_count,thank_to_count,thank_from_count,thanked_count,description,hosted_live_count,participated_live_count,allow_message,industry_category,org_name,org_homepage,badge[?(type=best_answerer)].topics' #个人信息链接
    def start_requests(self):
        yield Request(self.followees_url.format(user=self.start_user,offset=0),callback=self.parse_fo) #回调种子用户的关注列表
        yield Request(self.user_url.format(user=self.start_user,include = self.user_include),callback=self.parse_user) #回调种子用户的个人信息

    def parse_user(self, response):
        result = json.loads(response.text)
        print(result)
        item = ZhihuxjjItem()
        item['user_name'] = result['name']
        item['sex'] = result['gender']  # gender为1是男，0是女，-1是未设置
        item['user_sign'] = result['headline']
        item['user_avatar'] = result['avatar_url_template'].format(size='xl')
        item['user_url'] = 'https://www.zhihu.com/people/' + result['url_token']
        if len(result['locations']):
            item['user_add'] = result['locations'][0]['name']
        else:
            item['user_add'] = ''
        yield item

    def parse_fo(self, response):
        results = json.loads(response.text)
        for result in results['data']:
            yield Request(self.user_url.format(user=result['url_token'], include=self.user_include),callback=self.parse_user)
            yield Request(self.followees_url.format(user=result['url_token'], offset=0),callback=self.parse_fo)  # 对关注者的关注者进行遍历，爬取深度depth+=1
        if results['paging']['is_end'] is False: #关注列表页是否为尾页
            next_url = results['paging']['next'].replace('http','https')
            yield Request(next_url,callback=self.parse_fo)
        else:
            pass

import scrapy
class ZhihuxjjItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    user_name = scrapy.Field()
    sex  = scrapy.Field()
    user_sign = scrapy.Field()
    user_url = scrapy.Field()
    user_avatar = scrapy.Field()
    user_add = scrapy.Field()
    pass

import pymysql

def dbHandle():
    conn = pymysql.connect(
        host='localhost',
        user='root',
        passwd='数据库密码',
        charset='utf8',
        use_unicode=False
    )
    return conn

class ZhihuxjjPipeline(object):
    def process_item(self, item, spider):
        dbObject = dbHandle()  # 写入数据库
        cursor = dbObject.cursor()
        sql = "insert into xiaojiejie.zhihu(user_name,sex,user_sign,user_avatar,user_url,user_add) values(%s,%s,%s,%s,%s,%s)"
        param = (item['user_name'],item['sex'],item['user_sign'],item['user_avatar'],item['user_url'],item['user_add'])
        try:
            cursor.execute(sql, param)
            dbObject.commit()
        except Exception as e:
            print(e)
            dbObject.rollback()
        return item

DEFAULT_REQUEST_HEADERS = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36",
    'authorization': 'oauth c3cef7c66a1843f8b3a9e6a1e3160e20'
}

$ scrapy crawl zhihuxjj