scrapy爬取猫眼电影排行榜

1 # 创建爬虫项目
2 scrapy startproject Maoyan
3 cd Maoyan
4 # 创建爬虫文件
5 scrapy genspider maoyan maoyan.com

1 name = scrapy.Field()
2 star = scrapy.Field()
3 time = scrapy.Field()

 1 import scrapy
 2 from ..items import MaoyanItem
 3 ?
 4 class MaoyanSpider(scrapy.Spider):
 5     name = ‘maoyan3‘
 6     allowed_domains = [‘maoyan.com‘]
 7     # 去掉start_urls变量
 8 ?
 9     # 重写start_requests()方法
10     def start_requests(self):
11         for offset in range(0,91,10):
12             url = ‘https://maoyan.com/board/4?offset={}‘.format(offset)
13             yield scrapy.Request(url=url,callback=self.parse)
14 ?
15     def parse(self, response):
16         # 给items.py中的类:MaoyanItem(scrapy.Item)实例化
17         item = MaoyanItem()
18 ?
19         # 基准xpath
20         dd_list = response.xpath(‘//dl[@class="board-wrapper"]/dd‘)
21         # 依次遍历
22         for dd in dd_list:
23             # 是在给items.py中那些类变量赋值
24             item[‘name‘] = dd.xpath(‘./a/@title‘).get().strip()
25             item[‘star‘] = dd.xpath(‘.//p[@class="star"]/text()‘).get().strip()
26             item[‘time‘] = dd.xpath(‘.//p[@class="releasetime"]/text()‘).get().strip()
27 ?
28             # 把item对象交给管道文件处理
29             yield item

 1 class MaoyanPipeline(object):
 2     # item: 从爬虫文件maoyan.py中yield的item数据
 3     def process_item(self, item, spider):
 4         print(item[‘name‘],item[‘time‘],item[‘star‘])
 5 ?
 6         return item
 7 ?
 8 ?
 9 import pymysql
10 from .settings import *
11 ?
12 # 自定义管道 - MySQL数据库
13 class MaoyanMysqlPipeline(object):
14     # 爬虫项目开始运行时执行此函数
15     def open_spider(self,spider):
16         print(‘我是open_spider函数输出‘)
17         # 一般用于建立数据库连接
18         self.db = pymysql.connect(
19             host = MYSQL_HOST,
20             user = MYSQL_USER,
21             password = MYSQL_PWD,
22             database = MYSQL_DB,
23             charset = MYSQL_CHAR
24         )
25         self.cursor = self.db.cursor()
26 ?
27     def process_item(self,item,spider):
28         ins = ‘insert into filmtab values(%s,%s,%s)‘
29         # 因为execute()的第二个参数为列表
30         L = [
31             item[‘name‘],item[‘star‘],item[‘time‘]
32         ]
33         self.cursor.execute(ins,L)
34         self.db.commit()
35 ?
36         return item
37 ?
38     # 爬虫项目结束时执行此函数
39     def close_spider(self,spider):
40         print(‘我是close_spider函数输出‘)
41         # 一般用于断开数据库连接
42         self.cursor.close()
43         self.db.close()

 1 USER_AGENT = ‘Mozilla/5.0‘
 2 ROBOTSTXT_OBEY = False
 3 DEFAULT_REQUEST_HEADERS = {
 4   ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8‘,
 5   ‘Accept-Language‘: ‘en‘,
 6 }
 7 ITEM_PIPELINES = {
 8    ‘Maoyan.pipelines.MaoyanPipeline‘: 300,
 9    ‘Maoyan.pipelines.MaoyanMysqlPipeline‘:200,
10 }
11 # 定义MySQL相关变量
12 MYSQL_HOST = ‘127.0.0.1‘
13 MYSQL_USER = ‘root‘
14 MYSQL_PWD = ‘123456‘
15 MYSQL_DB = ‘maoyandb‘
16 MYSQL_CHAR = ‘utf8‘

1 from scrapy import cmdline
2 cmdline.execute(‘scrapy crawl maoyan‘.split())