Scrapy第一次爬虫（并将数据传到mysql中）

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy

class NewsItem(scrapy.Item):
    # define the fields for your item here like:
    new_title = scrapy.Field()
    new_time = scrapy.Field()
    new_href = scrapy.Field()
    content_img = scrapy.Field()
    content = scrapy.Field()

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40

# -*- coding: utf-8 -*-
import scrapy
from news.items import NewsItem

class NewSpider(scrapy.Spider):
    name = 'new'
    allowed_domains = ['hxfzzx.com'] # 爬虫域
    start_urls = ['http://www.hxfzzx.com/news/fzfj/']  # 开始爬取的地址

    def parse(self, response):
        li_list = response.xpath("//div[@class='zw']//li")  # 分析页面元素
        for li in li_list:
            item = NewsItem()
            item["new_title"] = li.xpath("./a/text()").extract_first()  # 分别取出新闻标题，新闻时间，新闻详情页地址
            item["new_time"] = li.xpath("./span/text()").extract_first()
            item["new_href"] = li.xpath("./a/@href").extract_first()
            if item["new_href"] is None:  # 因为此处会爬虫有None的数据，所以过滤一下
                continue

            # 发起一个请求，去获取详情页
            yield scrapy.Request(
                item["new_href"],
                callback=self.parse_detail,
                meta={"item": item}
            )

        # 遍历10页的内容
        next_url = response.xpath("//div[@id='pages']/a[@class='a1'][3]/@href").get()
        if next_url != "/news/fzfj/11.html":
            next_url = "http://www.hxfzzx.com"+next_url
            yield scrapy.Request(
                next_url,
                callback=self.parse
            )

    # 获取详情页信息
    def parse_detail(self, response):
        item = response.meta["item"]
        item["content"] = response.xpath("//div[@class='zw show']").extract()  # 获取详情页的内容，此处将他的div整个都爬了，方便格式
        yield item

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html

import pymysql

class NewsPipeline(object):
    def __init__(self):
        # 连接MySQL数据库
        self.connect = pymysql.connect(host='连接ip', user='用户名', password='密码', db='数据库名', port=3306)
        self.cursor = self.connect.cursor()

    def process_item(self, item, spider):
        # 往数据库里面写入数据
        sql = "insert into news(`new_title`, `new_time`, `new_href`, `content`) values (%s, %s, %s, %s)"
        self.cursor.execute(sql, (item['new_title'], item['new_time'], item['new_href'], item['content']))
        self.connect.commit()
        return item

    # 关闭数据库
    def close_spider(self, spider):
        self.cursor.close()
        self.connect.close()