新浪新闻全站

一.爬虫

# -*- coding: utf-8 -*-
import scrapy
import os
from sina.items import SinaItem


class SinapiderSpider(scrapy.Spider):
    name = 'sinapider'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['http://news.sina.com.cn/guide/']

    def parse(self, response):
        items = []
        # 所有大类的url 和 标题
        #返回值都是列表
        parentUrls = response.xpath('//div[@id="tab01"]/div/h3/a/@href').extract()
        parentTitle = response.xpath('//div[@id="tab01"]/div/h3/a/text()').extract()

        # 所有小类的ur 和 标题
        #返回值都是列表
        subUrls = response.xpath('//div[@id="tab01"]/div/ul/li/a/@href').extract()
        subTitle = response.xpath('//div[@id="tab01"]/div/ul/li/a/text()').extract()

        # 爬取所有大类
        for i in range(0, len(parentTitle)):
            # 指定大类目录的路径和目录名
            parentFilename = "./Data/" + parentTitle[i]

            # 如果目录不存在，则创建目录
            if (not os.path.exists(parentFilename)):
                os.makedirs(parentFilename)

            # 爬取所有小类
            for j in range(0, len(subUrls)):
                item = SinaItem()

                # 保存大类的title和urls
                #因为所有的小类的url在同一个列表，为了后面的判断是这个小类url是属于哪个父类的
                item['parentTitle'] = parentTitle[i]
                item['parentUrls'] = parentUrls[i]

                # 检查小类的url是否以同类别大类url开头，如果是返回True (sports.sina.com.cn 和 sports.sina.com.cn/nba)
                if_belong = subUrls[j].startswith(item['parentUrls'])

                # 如果属于本大类，将存储目录放在本大类目录下
                if (if_belong):
                    subFilename = parentFilename + '/' + subTitle[j]
                    # 如果目录不存在，则创建目录
                    if (not os.path.exists(subFilename)):
                        os.makedirs(subFilename)

                    # 存储 小类url、title和filename字段数据
                    item['subUrls'] = subUrls[j]
                    item['subTitle'] = subTitle[j]
                    item['subFilename'] = subFilename

                    items.append(item)

        # 发送每个小类url的Request请求，得到Response连同包含meta数据 一同交给回调函数 second_parse 方法处理
        for item in items:
            yield scrapy.Request(url=item['subUrls'], meta={'meta_1': item}, callback=self.second_parse)

    # 对于返回的小类的url，再进行递归请求
    def second_parse(self, response):
        # 提取每次Response的meta数据
        meta_1 = response.meta['meta_1']

        # 取出小类里所有子链接
        sonUrls = response.xpath('//a/@href').extract()

        items = []
        for i in range(0, len(sonUrls)):
            # 检查每个链接是否以大类url开头、以.shtml结尾，如果是返回True
            if_belong = sonUrls[i].endswith('.shtml') and sonUrls[i].startswith(meta_1['parentUrls'])

            # 如果属于本大类，获取字段值放在同一个item下便于传输
            if (if_belong):
                item = SinaItem()
                item['parentTitle'] = meta_1['parentTitle']
                item['parentUrls'] = meta_1['parentUrls']
                item['subUrls'] = meta_1['subUrls']
                item['subTitle'] = meta_1['subTitle']
                item['subFilename'] = meta_1['subFilename']
                item['sonUrls'] = sonUrls[i]
                items.append(item)

        # 发送每个小类下子链接url的Request请求，得到Response后连同包含meta数据 一同交给回调函数 detail_parse 方法处理
        for item in items:
            yield scrapy.Request(url=item['sonUrls'], meta={'meta_2': item}, callback=self.detail_parse)

    # 数据解析方法，获取文章标题和内容
    def detail_parse(self, response):
        item = response.meta['meta_2']
        content = ""
        head = response.xpath('//h1[@id="main_title"]/text()')
        content_list = response.xpath('//div[@id="artibody"]/p/text()').extract()

        # 将p标签里的文本内容合并到一起
        for content_one in content_list:
            content += content_one

        item['head'] = head
        item['content'] = content

        yield item         

二. item

import scrapy


class SinaItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    #大类标题和连接
    parentTitle = scrapy.Field()
    parentUrls = scrapy.Field()

    #小类标题和url
    subTitle=scrapy.Field()
    subUrls=scrapy.Field()

    #小类目录存储路径
    subFilename=scrapy.Field()

    #小类下的子连接
    sonUrls=scrapy.Field()


    #文章的标题和内容
    head=scrapy.Field()
    content=scrapy.Field()

3.pipeline

# -*- 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

class SinaPipeline(object):
    def process_item(self, item, spider):
        sonUrls = item['sonUrls']

        # 文件名为子链接url中间部分，并将 / 替换为 _，保存为 .txt格式
        filename = sonUrls[7:-6].replace('/', '_')
        filename += ".txt"

        fp = open(item['subFilename'] + '/' + filename, 'w',encoding='utf-8')
        fp.write(item['content'])
        fp.close()

        return item

4.settings

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

# Scrapy settings for sina 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 = 'sina'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0'

# 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 = {
#    'sina.middlewares.SinaSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'sina.middlewares.SinaDownloaderMiddleware': 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 = {
   'sina.pipelines.SinaPipeline': 300,
}

# 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'


LOG_LEVEL = 'DEBUG'