python实战项目scrapy管道学习爬取在行高手数据

class ZaihangItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()  # 姓名
    city = scrapy.Field()  # 城市
    industry = scrapy.Field()  # 行业
    price = scrapy.Field()  # 价格
    chat_nums = scrapy.Field()  # 聊天人数
    score = scrapy.Field()  # 评分

https://www.zaih.com/falcon/mentors?first_tag_id=479&first_tag_name=心理&page={}

import scrapy
from zaihang_spider.items import ZaihangItem
class ZhSpider(scrapy.Spider):
    name = 'zh'
    allowed_domains = ['www.zaih.com']
    page = 1  # 起始页码
    url_format = 'https://www.zaih.com/falcon/mentors?first_tag_id=479&first_tag_name=%E5%BF%83%E7%90%86&page={}'  # 模板
    start_urls = [url_format.format(page)]
    def parse(self, response):
        empty = response.css("section.empty") # 判断数据是否为空
        if len(empty) > 0:
            return # 存在空标签，直接返回
        mentors = response.css(".mentor-board a") # 所有高手的超链接
        for m in mentors:
            item = ZaihangItem() # 实例化一个对象
            name = m.css(".mentor-card__name::text").extract_first()
            city = m.css(".mentor-card__location::text").extract_first()
            industry = m.css(".mentor-card__title::text").extract_first()
            price = self.replace_space(m.css(".mentor-card__price::text").extract_first())
            chat_nums = self.replace_space(m.css(".mentor-card__number::text").extract()[0])
            score = self.replace_space(m.css(".mentor-card__number::text").extract()[1])
            # 格式化数据
            item["name"] = name
            item["city"] = city
            item["industry"] = industry
            item["price"] = price
            item["chat_nums"] = chat_nums
            item["score"] = score
            yield item
        # 再次生成一个请求
        self.page += 1
        next_url = format(self.url_format.format(self.page))
        yield scrapy.Request(url=next_url, callback=self.parse)
    def replace_space(self, in_str):
        in_str = in_str.replace("\n", "").replace("\r", "").replace("￥", "")
        return in_str.strip()

ITEM_PIPELINES = {
   'zaihang_spider.pipelines.ZaihangMySQLPipeline': 300,
}

@classmethod
def from_settings(cls, settings):
    host= settings.get('HOST')
    return cls(host)

@classmethod
def from_crawler(cls, crawler):
  # FIXME: for now, stats are only supported from this constructor
  return cls.from_settings(crawler.settings)

HOST = "127.0.0.1"
PORT = 3306
USER = "root"
PASSWORD = "123456"
DB = "zaihang"

import pymysql
class ZaihangMySQLPipeline:
    def __init__(self, host, port, user, password, db):
        self.host = host
        self.port = port
        self.user = user
        self.password = password
        self.db = db
        self.conn = None
        self.cursor = None
    @classmethod
    def from_crawler(cls, crawler):
        return cls(
            host=crawler.settings.get('HOST'),
            port=crawler.settings.get('PORT'),
            user=crawler.settings.get('USER'),
            password=crawler.settings.get('PASSWORD'),
            db=crawler.settings.get('DB')
        )
    def open_spider(self, spider):
        self.conn = pymysql.connect(host=self.host, port=self.port, user=self.user, password=self.password, db=self.db)
    def process_item(self, item, spider):
        # print(item)
        # 存储到 MySQL
        name = item["name"]
        city = item["city"]
        industry = item["industry"]
        price = item["price"]
        chat_nums = item["chat_nums"]
        score = item["score"]
        sql = "insert into users(name,city,industry,price,chat_nums,score) values ('%s','%s','%s',%.1f,%d,%.1f)" % (
            name, city, industry, float(price), int(chat_nums), float(score))
        print(sql)
        self.cursor = self.conn.cursor()  # 设置游标
        try:
            self.cursor.execute(sql)  # 执行 sql
            self.conn.commit()
        except Exception as e:
            print(e)
            self.conn.rollback()
        return item
    def close_spider(self, spider):
        self.cursor.close()
        self.conn.close()

# 爬虫开启时执行，只执行一次
def open_spider(self, spider):
    # spider.name = "橡皮擦"  # spider对象动态添加实例变量，可以在spider模块中获取该变量值，比如在 parse(self, response) 函数中通过self 获取属性
    # 一些初始化动作
    pass

# 处理提取的数据，数据保存代码编写位置
def process_item(self, item, spider):
    pass

# 爬虫关闭时执行，只执行一次，如果爬虫运行过程中发生异常崩溃，close_spider 不会执行
def close_spider(self, spider):
    # 关闭数据库，释放资源
    pass