爬取网易新闻

创建项目：

scrapy startproject wangyi

创建虫子：

scrapy genspider wangyi www.xxx.com :创建爬虫文件

执行：scrapy crawl spiderName

wangyi.py 虫子

# -*- coding: utf-8 -*-
import scrapy
from selenium import webdriver
from wangyiPeo1.items import Wangyipeo1Item


class WangyiSpider(scrapy.Spider):
    name = 'wangyi'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://news.163.com/']
    model_urls = []
    bro = webdriver.Chrome()

    def parse(self, response):
        # 解析出5个板块对应的url：
        li_list = response.xpath('//*[@id="index2016_wrap"]/div[1]/div[2]/div[2]/div[2]/div[2]/div/ul/li')
        model_index = [3, 4, 6, 7, 8]
        for index in model_index:
            # li依次表示是5个板块对应的li标签：
            li = li_list[index]
            # 解析每个url：
            model_url = li.xpath("./a/@href").extract_first()
            self.model_urls.append(model_url)
            # 手动请求发送每个板块对应的url：
            yield scrapy.Request(model_url, callback=self.parse_model)

    def parse_model(self, response):
        """
        用于解析每个板块对应的页面数据中的新闻标题和详情页的url
        该方法中获取的response对象是没有包含动态加载出的新闻数据（是一个不满足需求的response）
        """
        div_list = response.xpath('/html/body/div/div[3]/div[4]/div[1]/div/div/ul/li/div/div')
        for div in div_list:
            # 标题：
            title = div.xpath('./div/div[1]/h3/a/text()').extract_first()
            # 标题的url：
            detail_url = div.xpath('./a/@href').extract_first()
            item = Wangyipeo1Item()
            item['title'] = title
            # 手动发请求：
            yield scrapy.Request(detail_url, callback=self.parse_new_detail, meta={'item': item})

    def parse_new_detail(self, response):
        """用于解析新闻内容"""
        item = response.meta['item']
        content = response.xpath('//*[@id="endText"]//text()').extract()
        content = ''.join(content)
        item['content'] = content
        yield item

    def closed(self, spider):
        # 关闭解析、该方法只会在整个程序结束时执行一次
        self.bro.quit()

items.py

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

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

import scrapy


class Wangyipeo1Item(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    content = scrapy.Field()

middlewares.py请求响应

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

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
import time
from scrapy import signals
from scrapy.http import HtmlResponse
from time import sleep


class Wangyipeo1DownloaderMiddleware(object):
    # 参数：
    # reuqest:拦截到请求对应的响应对象
    # response：拦截到所有的响应对象（1+5+n）
    # spider：爬虫类实例化的对象，可以实现爬虫类和中间件类的数据交互
    def process_response(self, request, response, spider):
        # 拦截到5个板块对应的响应对象，将其替换成5个符合需求的新的响应对象进行返回
        # 1.找出5个板块对应的5个不符合需求的响应对象
        if request.url in spider.model_urls:
            # 就是满足需求的五个板块对应的响应对象
            # url:响应对象对应的请求对象的url
            # body:响应数据,可以由selenium中的page_source返回
            bro = spider.bro
            bro.get(request.url)
            time.sleep(1)
            page_text = bro.page_source  # 获取到源码数据(包含动态加载的新闻数据)
            new_response = HtmlResponse(url=request.url, body=page_text, encoding="utf-8", request=request)
            return new_response
        else:
            return response

pipelines.py管道

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

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


class Wangyipeo1Pipeline(object):
    # 定义数据库初始状态：
    conn = None
    # 定义游标：
    curse = None

    def open_spider(self, spider):
        # 连接数据库：
        self.conn = pymysql.Connect(host="127.0.0.1", port=3306, user="root", password="123", db="Spider",
                                    charset="utf8")
        print(self.conn)

    def process_item(self, item, spider):
        """插入数据"""
        print(item)
        sql = 'insert into wangyi value ("%s","%s")' % (item["title"], item["content"])
        self.curse = self.conn.cursor()
        try:
            self.curse.execute(sql)
            self.conn.commit()
        except Exception as e:
            print(e)
            self.conn.rollback()
        return item

    def close_spider(self, spider):
        """关闭数据库连接状态"""
        self.curse.close()
        self.conn.close()

settings.py配置文件

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

# Scrapy settings for wangyiPeo1 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'wangyiPeo1'

SPIDER_MODULES = ['wangyiPeo1.spiders']
NEWSPIDER_MODULE = 'wangyiPeo1.spiders'

# UA伪装：
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'wangyiPeo1 (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 日志级别：
LOG_LEVEL = 'ERROR'

# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
# CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
# COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
# TELNETCONSOLE_ENABLED = False

# Override the default request headers:
# DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
# }

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    'wangyiPeo1.middlewares.Wangyipeo1SpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# 开启下载管道：
DOWNLOADER_MIDDLEWARES = {
    'wangyiPeo1.middlewares.Wangyipeo1DownloaderMiddleware': 543,
}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
# }

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
# 开启数据管道
ITEM_PIPELINES = {
    'wangyiPeo1.pipelines.Wangyipeo1Pipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
# AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
# HTTPCACHE_ENABLED = True
# HTTPCACHE_EXPIRATION_SECS = 0
# HTTPCACHE_DIR = 'httpcache'
# HTTPCACHE_IGNORE_HTTP_CODES = []
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

猜你喜欢