scrapy (三) : 请求传参
2024-09-06 00:09:07
scrapy 请求传参
1.定义数据结构item.py文件
'''
field: item.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 MovieprojectItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
# 电影海报
# 一级页面要抓取的内容
post = scrapy.Field()
name = scrapy.Field()
_type = scrapy.Field()
# 二级页面要抓取的内容
director = scrapy.Field()
design = scrapy.Field()
actor = scrapy.Field()
info = scrapy.Field()
2.爬虫文件
# -*- coding: utf-8 -*-
# -*- coding: utf-8 -*-
import scrapy
from movieproject.items import MovieprojectItem
class MovieSpider(scrapy.Spider):
name = 'movie'
allowed_domains = ['www.id97.com']
start_urls = ['http://www.id97.com/movie/']
url = 'http://www.id97.com/movie/?page={}'
page = 1
'''
(1)只需要提取页码链接,只提取第一页的信息即可
(2)需要写两个规则,一个规则提取详情页面,一个规则是提取页码链接
'''
def parse(self, response):
# 先查找所有的movie_div
movie_div_list = response.xpath('//div[starts-with(@class,"col-xs-1-5")]')
# 遍历所有的div,去获取每一个详细的信息
for odiv in movie_div_list:
item = MovieprojectItem()
# 获取电影海报
item['post'] = odiv.xpath(".//img/@data-original").extract_first()
# 获取电影名字
item['name'] = odiv.xpath("./div/div/h1/a/text()").extract_first()
# 获取电影类型
item['_type'] = odiv.xpath("./div/div/div/a/text()").extract()
# 获取详情页面
detail_href = odiv.xpath('./div/a/@href').extract_first()
'''
向详情页面发送请求
将item向二级传递过去,到二级页面接受并且接着提取其他的信息
请求二级详情页面,解析二级页面中的相应内容,通过meta参数进行Request的数据传
'''
yield scrapy.Request(url=detail_href,callback=self.parse_detail, meta={'item': item})
# 爬取其他页面
if self.page <= 5:
self.page += 1
url = self.url.format(self.page)
print(url)
yield scrapy.Request(url=url, callback=self.parse)
def parse_detail(self,response):
# 首先获取到上一级传递过来的item
item = response.meta['item']
# 在这个页面中接着提取电影的其它信息即可
# 获取导演
item['director'] = response.xpath("//div[starts-with(@class,'col-xs-8')]/table/tbody/tr/td[2]/a/text()").extract()
# 获取编剧
item['design'] = response.xpath("//div[starts-with(@class,'col-xs-8')]/table/tbody/tr[2]/td[2]/a/text()").extract()
# 获取主演
item['actor'] = response.xpath("//div[starts-with(@class,'col-xs-8')]/table/tbody/tr[3]/td[2]/a/text()").extract()
# 获取电影介绍
item['info'] = response.xpath("//div[@class='col-xs-12 movie-introduce']/p/text()").extract_first()
#提交item到管道
yield item
3.管道文件
# -*- coding: utf-8 -*-
'''
filed: pipelines.py
'''
# -*- 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 json
from scrapy.utils.project import get_project_settings
import pymysql
class MovieprojectPipeline(object):
def open_spider(self,spider):
self.fp = open("movie.json","w",encoding="utf8")
def process_item(self, item, spider):
obj = dict(item)
string = json.dumps(obj,ensure_ascii=False)
self.fp.write(string+'\n')
# print("写入成功")
return item
def close_spider(self,spider):
self.fp.close()
class MovieMysqlPipeline(object):
def open_spider(self,spider):
# 获取所有的配置信息
settings = get_project_settings()
# 链接数据库
host = settings['DB_HOST']
port = settings['DB_PORT']
user = settings['DB_USER']
pwd = settings['DB_PWD']
name = settings['DB_NAME']
charset = settings['DB_CHARSET']
self.conn = pymysql.connect(host=host, port=port, user=user, password=pwd, db=name, charset=charset)
def process_item(self, item, spider):
# 拼接sql语句
sql = 'insert into movie(post, name, type, director, design, actor, info) values("%s","%s","%s","%s","%s","%s","%s")' % (item['post'], item['name'], item['_type'], item['director'], item['design'], item['actor'], item['info'])
# 获取游标
cursor = self.conn.cursor()
# 执行sql语句
try:
cursor.execute(sql)
self.conn.commit()
except Exception as e:
self.conn.rollback()
return item
def close_spider(self,spider):
# 关闭数据库
self.conn.close()
最新文章
- RAM、DRAM、SD卡
- GitHub Pages 搭建流程-基于jekyll-bootstrap
- Android 网络编程基础之简单聊天程序
- quick sort java version
- 数据库配置文件 conf.properties
- C++语言中cin cin.getline cin.get getline gets getchar 的用法实例
- if语句使用
- 模板template
- 彷徨中的成长-记一个文科生的IT成长过程
- Windows下使用NCL(Cygwin模拟Linux环境)
- java functional syntax overview
- UVA 11549 CALCULATOR CONUNDRUM(Floyd判圈算法)
- vue ajax获取数据的时候,如何保证传递参数的安全或者说如何保护api的安全
- (八十六)使用系统自带的分享框架Social.framework
- python11 函数的定义,调用,分类
- VS之设置文件编码格式
- 在linux和windows用c++编写c接口的动态库
- 【问题解决:启动卡死】Eclipse启动卡死的解决办法
- 2、以自定义struct或struct指针作为map的Key
- phpize增加php模块