Scrapy爬豆瓣电影Top250并存入MySQL数据库
d:
进入D盘
scrapy startproject douban
创建豆瓣项目
cd douban
进入项目
scrapy genspider douban_spider movie.douban.com
创建爬虫
编辑items.py：
# -*- 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 DoubanItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
serial_number = scrapy.Field()
# 序号
movie_name = scrapy.Field()
# 电影的名称
introduce = scrapy.Field()
# 电影的介绍
star = scrapy.Field()
# 星级
evaluate = scrapy.Field()
# 电影的评论数
depict = scrapy.Field()
# 电影的描述
编辑douban_spider.py：
# -*- coding: utf-8 -*-
import scrapy
from douban.items import DoubanItem
class DoubanSpiderSpider(scrapy.Spider):
name = 'douban_spider'
# 爬虫的名字
allowed_domains = ['movie.douban.com']
# 允许的域名
start_urls = ['https://movie.douban.com/top250']
# 引擎入口url，扔到调度器里面去
def parse(self, response):
# 默认的解析方法
movie_list = response.xpath(".//*[@id='content']/div/div[1]/ol/li")
# 第一页展示的电影的列表
for i_item in movie_list:
# 循环电影的条目
douban_item = DoubanItem()
# 实例化DoubanItem()
douban_item["serial_number"] = i_item.xpath(".//div/div[1]/em/text()").extract_first()
douban_item["movie_name"] = i_item.xpath(".//div/div[2]/div[1]/a/span[1]/text()").extract_first()
content = i_item.xpath(".//div/div[2]/div[2]/p[1]/text()").extract()
for i_content in content:
# 处理电影的介绍中的换行的数据
content_s = "".join(i_content.split())
douban_item["introduce"] = content_s
douban_item["star"] = i_item.xpath(".//div/div[2]/div[2]/div/span[2]/text()").extract_first()
douban_item["evaluate"] = i_item.xpath(".//div/div[2]/div[2]/div/span[4]/text()").extract_first()
douban_item["depict"] = i_item.xpath(".//div/div[2]/div[2]/p[2]/span/text()").extract_first()
yield douban_item
# 需要把数据yield到pipelines里面去
next_link = response.xpath(".//*[@id='content']/div/div[1]/div[2]/span[3]/a/@href").extract()
# 解析下一页，取后页的xpath
if next_link:
next_link = next_link[0]
yield scrapy.Request("https://movie.douban.com/top250" + next_link, callback=self.parse)
新建MySQLPipline.py：
from pymysql import connect
class MySQLPipeline(object):
def __init__(self):
self.connect = connect(
host='192.168.1.23',
port=3306,
db='scrapy',
user='root',
passwd='Abcdef@123456',
charset='utf8',
use_unicode=True)
# 连接数据库
self.cursor = self.connect.cursor()
# 使用cursor()方法获取操作游标
def process_item(self, item, spider):
self.cursor.execute(
"""insert into douban(serial_number, movie_name, introduce, star, evaluate, depict)
value (%s, %s, %s, %s, %s, %s)""",
(item['serial_number'],
item['movie_name'],
item['introduce'],
item['star'],
item['evaluate'],
item['depict']
))
# 执行sql语句，item里面定义的字段和表字段一一对应
self.connect.commit()
# 提交
return item
# 返回item
def close_spider(self, spider):
self.cursor.close()
# 关闭游标
self.connect.close()
# 关闭数据库连接
新建UserAgentMiddleware.py：
import random
class UserAgentMiddleware(object):
def process_request(self, request, spider):
user_agent_list = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"
]
agent = random.choice(user_agent_list)
request.headers["User-Agent"] = agent
修改settings.py配置文件：
第57行修改为：
DOWNLOADER_MIDDLEWARES = {
'douban.UserAgentMiddleware.UserAgentMiddleware': 543,
}
# 启用middleware
第69行修改为：
ITEM_PIPELINES = {
'douban.MySQLPipline.MySQLPipeline': 300,
}
# 启用pipeline
CREATE DATABASE scrapy;
创建数据库
CREATE TABLE `douban` (
`id` INT(11) NOT NULL AUTO_INCREMENT,
`serial_number` INT(11) DEFAULT NULL COMMENT '序号',
`movie_name` VARCHAR(255) DEFAULT NULL COMMENT '电影的名称',
`introduce` VARCHAR(255) DEFAULT NULL COMMENT '电影的介绍',
`star` VARCHAR(255) DEFAULT NULL COMMENT '星级',
`evaluate` VARCHAR(255) DEFAULT NULL COMMENT '电影的评论数',
`depict` VARCHAR(255) DEFAULT NULL COMMENT '电影的描述',
PRIMARY KEY (`id`)
) ENGINE=INNODB DEFAULT CHARSET=utf8 COMMENT '豆瓣表';
创建表
scrapy crawl douban_spider --nolog
运行爬虫（不打印日志）
