python scrapy 实战简书网站

 

1:创建项目

2：创建爬虫

3：编写start.py文件用于运行爬虫程序

# -*- coding:utf-8 -*-
#作者:    baikai  
#创建时间: 2018/12/14 14:09 
#文件:    start.py  
#IDE:    PyCharm
from scrapy import cmdline

cmdline.execute("scrapy crawl js".split())

4：设置settings.py文件的相关设置

爬取详情页数据

编写items.py文件

# -*- 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 ArticleItem(scrapy.Item):
    # 定义我们需要的存储数据字段
    title=scrapy.Field()
    content=scrapy.Field()
    article_id=scrapy.Field()
    origin_url=scrapy.Field()
    author=scrapy.Field()
    avatar=scrapy.Field()
    pub_time=scrapy.Field()

编写js.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from jianshu_spider.items import ArticleItem

class JsSpider(CrawlSpider):
    name = 'js'
    allowed_domains = ['jianshu.com']
    start_urls = ['https://www.jianshu.com/']

    rules = (
        # 匹配地址https://www.jianshu.com/p/d8804d18d638
        Rule(LinkExtractor(allow=r'.*/p/[0-9a-z]{12}.*'), callback='parse_detail', follow=True),
    )

    def parse_detail(self, response):
        # 获取内容页数据并解析数据
        title=response.xpath("//h1[@class='title']/text()").get()
        #作者图像
        avatar=response.xpath("//a[@class='avatar']/img/@src").get()
        author=response.xpath("//span[@class='name']/a/text()").get()
        #发布时间
        pub_time=response.xpath("//span[@class='publish-time']/text()").get()
        #详情页id
        url=response.url
        #https://www.jianshu.com/p/d8804d18d638
        url1=url.split("?")[0]
        article_id=url1.split("/")[-1]
        #文章内容
        content=response.xpath("//div[@class='show-content']").get()

        item=ArticleItem(
            title=title,
            avatar=avatar,
            author=author,
            pub_time=pub_time,
            origin_url=response.url,
            article_id=article_id,
            content=content
        )
        yield item

 

设计数据库和表

数据库jianshu

表article

id设置为自动增长

 

 将爬取到的数据存储到mysql数据库中

 

# -*- 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
from twisted.enterprise import adbapi
from pymysql import cursors

class JianshuSpiderPipeline(object):
    def __init__(self):
        dbparams = {
            'host': '127.0.0.1',
            'port': 3306,
            'user': 'root',
            'password': '8Wxx.ypa',
            'database': 'jianshu',
            'charset': 'utf8'
        }
        self.conn = pymysql.connect(**dbparams)
        self.cursor = self.conn.cursor()
        self._sql = None

    def process_item(self, item, spider):
        self.cursor.execute(self.sql, (item['title'], item['content'], item['author'], item['avatar'], item['pub_time'], item['origin_url'],item['article_id']))
        self.conn.commit()
        return item

    @property
    def sql(self):
        if not self._sql:
            self._sql = """
                insert into article(id,title,content,author,avatar,pub_time,origin_url,article_id) values(null,%s,%s,%s,%s,%s,%s,%s)
                """
            return self._sql
        return self._sql

运行start.py效果如下