(實戰(zhàn)項目三)新浪網(wǎng)分類資訊爬蟲

爬取新浪網(wǎng)導航頁所有下所有大類、小類侦锯、小類里的子鏈接驼鞭，以及子鏈接頁面的新聞內(nèi)容。

效果演示圖：

day55_爬蟲-scrapy實戰(zhàn)項目-01.png

items.py

import scrapy
import sys
reload(sys)
sys.setdefaultencoding("utf-8")

class SinaItem(scrapy.Item):
    # 大類的標題 和 url
    parentTitle = scrapy.Field()
    parentUrls = scrapy.Field()

    # 小類的標題 和 子url
    subTitle = scrapy.Field()
    subUrls = scrapy.Field()

    # 小類目錄存儲路徑
    subFilename = scrapy.Field()

    # 小類下的子鏈接
    sonUrls = scrapy.Field()

    # 文章標題和內(nèi)容
    head = scrapy.Field()
    content = scrapy.Field()

spiders/sina.py

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

from Sina.items import SinaItem
import scrapy
import os

import sys
reload(sys)
sys.setdefaultencoding("utf-8")

class SinaSpider(scrapy.Spider):
    name= "sina"
    allowed_domains= ["sina.com.cn"]
    start_urls= [
       "http://news.sina.com.cn/guide/"
    ]

    def parse(self, response):
        items= []
        # 所有大類的url 和 標題
        parentUrls = response.xpath('//div[@id=\"tab01\"]/div/h3/a/@href').extract()
        parentTitle = response.xpath("http://div[@id=\"tab01\"]/div/h3/a/text()").extract()

        # 所有小類的ur 和 標題
        subUrls  = response.xpath('//div[@id=\"tab01\"]/div/ul/li/a/@href').extract()
        subTitle = response.xpath('//div[@id=\"tab01\"]/div/ul/li/a/text()').extract()

        #爬取所有大類
        for i in range(0, len(parentTitle)):
            # 指定大類目錄的路徑和目錄名
            parentFilename = "./Data/" + parentTitle[i]

            #如果目錄不存在尺碰，則創(chuàng)建目錄
            if(not os.path.exists(parentFilename)):
                os.makedirs(parentFilename)

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

                # 保存大類的title和urls
                item['parentTitle'] = parentTitle[i]
                item['parentUrls'] = parentUrls[i]

                # 檢查小類的url是否以同類別大類url開頭终议，如果是返回True (sports.sina.com.cn 和 sports.sina.com.cn/nba)
                if_belong = subUrls[j].startswith(item['parentUrls'])

                # 如果屬于本大類，將存儲目錄放在本大類目錄下
                if(if_belong):
                    subFilename =parentFilename + '/'+ subTitle[j]
                    # 如果目錄不存在葱蝗，則創(chuàng)建目錄
                    if(not os.path.exists(subFilename)):
                        os.makedirs(subFilename)

                    # 存儲 小類url穴张、title和filename字段數(shù)據(jù)
                    item['subUrls'] = subUrls[j]
                    item['subTitle'] =subTitle[j]
                    item['subFilename'] = subFilename

                    items.append(item)

        #發(fā)送每個小類url的Request請求，得到Response連同包含meta數(shù)據(jù) 一同交給回調(diào)函數(shù) second_parse 方法處理
        for item in items:
            yield scrapy.Request( url = item['subUrls'], meta={'meta_1': item}, callback=self.second_parse)

    #對于返回的小類的url两曼，再進行遞歸請求
    def second_parse(self, response):
        # 提取每次Response的meta數(shù)據(jù)
        meta_1= response.meta['meta_1']

        # 取出小類里所有子鏈接
        sonUrls = response.xpath('//a/@href').extract()

        items= []
        for i in range(0, len(sonUrls)):
            # 檢查每個鏈接是否以大類url開頭皂甘、以.shtml結(jié)尾，如果是返回True
            if_belong = sonUrls[i].endswith('.shtml') and sonUrls[i].startswith(meta_1['parentUrls'])

            # 如果屬于本大類悼凑，獲取字段值放在同一個item下便于傳輸
            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)

        #發(fā)送每個小類下子鏈接url的Request請求偿枕，得到Response后連同包含meta數(shù)據(jù) 一同交給回調(diào)函數(shù) detail_parse 方法處理
        for item in items:
                yield scrapy.Request(url=item['sonUrls'], meta={'meta_2':item}, callback = self.detail_parse)

    # 數(shù)據(jù)解析方法璧瞬，獲取文章標題和內(nèi)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()

        # 將p標簽里的文本內(nèi)容合并到一起
        for content_one in content_list:
            content += content_one

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

        yield item

pipelines.py

from scrapy import signals
import sys
reload(sys)
sys.setdefaultencoding("utf-8")

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

        # 文件名為子鏈接url中間部分，并將 / 替換為 _渐夸，保存為 .txt格式
        filename = sonUrls[7:-6].replace('/','_')
        filename += ".txt"

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

        return item

settings.py

BOT_NAME = 'Sina'

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

ITEM_PIPELINES = {
    'Sina.pipelines.SinaPipeline': 300,
}

LOG_LEVEL = 'DEBUG'

在項目根目錄下新建main.py文件,用于調(diào)試

from scrapy import cmdline
cmdline.execute('scrapy crawl sina'.split())

執(zhí)行程序

py2 main.py