网易新闻爬取

项目目录

创建项目

scrapy startproject wangyiPro

进入项目

cd wangyiPro

创建项目文件

scrapy genspider wangyi www.xxx.com

创建启动文件

start.py

from scrapy import cmdline
cmdline.execute("scrapy crawl wangyi".split())

 配置文件

setting.py

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

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

BOT_NAME = 'wangyiPro'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"

LOG_LEVEL = "ERROR"
# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'wangyiPro.middlewares.WangyiproSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543,
}

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

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'wangyiPro.pipelines.WangyiproPipeline': 300,
   'wangyiPro.pipelines.MysqlPipeline': 301,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.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://doc.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'

wangyi.py

# -*- coding: utf-8 -*-
import scrapy
from selenium import webdriver
from wangyiPro.items import WangyiproItem


class WangyiSpider(scrapy.Spider):
    name = 'wangyi'
    # allowed_domains = ['www.xx.com']
    start_urls = ['https://news.163.com/']
    bro = webdriver.Chrome(executable_path='chromedriver.exe')
    urls = []
    def parse(self, response):
        li_list = response.xpath('//*[@id="index2016_wrap"]/div[1]/div[2]/div[2]/div[2]/div[2]/div/ul/li')
        for index in [3,4,6,7,8]:
            li = li_list[index]
            new_url = li.xpath('./a/@href').extract_first()
            self.urls.append(new_url)
            yield scrapy.Request(url=new_url,callback=self.parse_news)

    def parse_news(self,response):
        div_list = response.xpath('//div[@class="ndi_main"]/div')
        for div in div_list:
            title = div.xpath('./div/div[1]/h3/a/text()').extract_first()
            news_detail_url = div.xpath('./div/div[1]/h3/a/@href').extract_first()
            item = WangyiproItem()
            item['title'] = title
            yield scrapy.Request(url=news_detail_url,callback=self.parse_detail,meta={'item':item})

    def parse_detail(self,response):
        item = response.meta['item']
        content = response.xpath('//div[@id="endText"]//text()').extract()
        content = "".join(content)
        item['content'] = content
        yield item

    def closed(self, spider):
        print("爬取完毕")
        self.bro.quit()

下载 chromedriver.zip

items.py

import scrapy
class WangyiproItem(scrapy.Item):

    title = scrapy.Field()
    content = scrapy.Field()

middlewares.py

from time import sleep
from scrapy.http import HtmlResponse
class WangyiproDownloaderMiddleware(object):

    def process_request(self, request, spider):

        return None

    def process_response(self, request, response, spider):
        if request.url in spider.urls:
            bro = spider.bro
            bro.get(request.url)
            try:
                bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
                sleep(1)
                bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
                sleep(1)
                bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
                sleep(1)
                bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
                sleep(1)
            except Exception as e:
                pass

            page_text = bro.page_source
            new_response = HtmlResponse(url=request.url,body=page_text,encoding='utf-8',request=request)
            return new_response
        else:
            return response

    def process_exception(self, request, exception, spider):

        pass

pipelines.py

import pymysql
class WangyiproPipeline(object):
    def process_item(self, item, spider):
        return item

class MysqlPipeline(object):
    conn = None
    cursor = None
    def open_spider(self,spider):
        self.conn = pymysql.Connect(host='127.0.0.1',port=3306,user = 'root',password= '',db='db',charset = 'utf8')
        print(self.conn)

    def process_item(self, item, spider):
        self.cursor = self.conn.cursor()
        try:
            self.cursor.execute('insert into wy(title,content) values ("%s","%s")'%(item['title'],item['content']))
            print("ok")
            self.conn.commit()
        except Exception as e:
            self.conn.rollback()
        return item

    def close_spider(self,spider):
        self.cursor.close()
        self.conn.close()