<scrapy爬虫>爬取360妹子图存入mysql(mongoDB还没学会,学会后加上去)

1.创建scrapy项目

dos窗口输入:

scrapy startproject images360

cd images360

2.编写item.py文件(相当于编写模板,需要爬取的数据在这里定义)

import scrapy


class Images360Item(scrapy.Item):
    # define the fields for your item here like:
    #图片ID
    image_id = scrapy.Field()
    #链接
    url = scrapy.Field()
    #标题
    title = scrapy.Field()
    #缩略图
    thumb = scrapy.Field()

　　

　　

3.创建爬虫文件

dos窗口输入:

scrapy genspider myspider images.so.com

4.编写myspider.py文件(接收响应,处理数据)

# -*- coding: utf-8 -*-
from urllib.parse import urlencode
import scrapy
from images360.items import Images360Item
import json


class MyspiderSpider(scrapy.Spider):
    name = 'myspider'
    allowed_domains = ['images.so.com']
    urls = []
    data = {'ch': 'beauty', 'listtype': 'new'}
    base_url = 'https://image.so.com/zj?0'
    for page in range(1,51):
        data['sn'] = page * 30
        params = urlencode(data)
        url = base_url + params
        urls.append(url)
    print(urls)
    start_urls = urls
    
    # ch: beauty
    # sn: 120
    # listtype: new
    # temp: 1
    
    def parse(self, response):
        result = json.loads(response.text)
        for each in result.get('list'):
            item = Images360Item()
            item['image_id'] = each.get('imageid')
            item['url'] = each.get('qhimg_url')
            item['title'] = each.get('group_title')
            item['thumb'] = each.get('qhimg_thumb_url')
            yield item

　　

5.编写pipelines.py(存储数据)

import pymysql.cursors


class Images360Pipeline(object):
    def __init__(self):
        self.connect = pymysql.connect(
            host='localhost',
            user='root',
            password='',
            database='quotes',
            charset='utf8',
        )
        self.cursor = self.connect.cursor()
    
    def process_item(self, item, spider):
        item = dict(item)
        sql = 'insert into images360(image_id,url,title,thumb) values(%s,%s,%s,%s)'
        self.cursor.execute(sql, (item['image_id'], item['url'], item['title'],item['thumb']))
        self.connect.commit()
        return item
    
    def close_spider(self, spider):
        self.cursor.close()
        self.connect.close()

　　

　　

6.编写settings.py(设置headers,pipelines等)

robox协议

# Obey robots.txt rules
ROBOTSTXT_OBEY = False　　

headers

DEFAULT_REQUEST_HEADERS = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  # 'Accept-Language': 'en',
}

pipelines

ITEM_PIPELINES = {
   'quote.pipelines.Images360Pipeline': 300,
}

　　

7.运行爬虫

dos窗口输入:

scrapy crawl myspider　

运行结果