python爬虫实例——用scarpy框架爬取全部新浪新闻

使用scrapy框架爬取新浪网导航页所有的大类，小类的子链接，取出链接页面新闻内容。

python版本3.5

注意点：spider文件中不写allowed domains,因为后面的子链接的url中跟不包含new.sina.com

爬虫运行报错：DEBUG: Filtered offsite request to 'weixin.sogou.com'

报错原因：
官方对这个的解释，是要request的地址和allow_domain里面的冲突，从而被过滤掉。

回头细查，在爬虫.py里面，明显将搜狗的域名写错，写成了“sougou.com”,而后面要爬取的url是“sogou.com/xxxxxx”,所以报错。

首先终端中运行 scrapy startproject sinanews (项目名)

然后spider文件夹中创建爬虫  scrapy genspider sina  ‘new.sina.com’

tree 一下(已经写好的项目)

.
├── main.py
├── scrapy.cfg
└── sinanews
    ├── __init__.py
    ├── __pycache__
    │   ├── __init__.cpython-36.pyc
    │   ├── items.cpython-36.pyc
    │   ├── pipelines.cpython-36.pyc
    │   └── settings.cpython-36.pyc
    ├── items.py
    ├── middlewares.py
    ├── pipelines.py
    ├── settings.py
    └── spiders
        ├── __init__.py
        ├── __pycache__
        │   ├── __init__.cpython-36.pyc
        │   └── sina.cpython-36.pyc
        └── sina.py

编辑items.py

定义好要爬取的url和标题名称（创建文件夹用）  以及文章内容和标题

import scrapy


class SinanewsItem(scrapy.Item):

    # 大类的标题 和 url
    parentTitle = scrapy.Field()
    parentUrls = scrapy.Field()

    # 小类的标题 和 url
    subTitle= scrapy.Field()
    subUrls = scrapy.Field()

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

    # 小类下的子链接
    sonUrls = scrapy.Field()

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

spider.py文件中全部代码

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


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

    def parse(self, response):
        items = []
        # 所有大类的url 和 标题
        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url 和 标题
        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 = "/Users/apple/Desktop/sina/" + 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 = SinanewsItem()
                # 保存大类的title和urls
                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
                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)

            # 发送每个小类的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)

    def second_parse(self,response):
        # 提取每次Response的meta数据
        meta_1 = response.meta['meta_1']
        # 取出小类里面的所有子链接
        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 = SinanewsItem()
                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
        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[@class="main-title"]/text()').extract()
        content_list = response.xpath("//div[@class='article']//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

pipelines.py文件全部代码

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

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals


class SinanewsSpiderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, dict or Item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Response, dict
        # or Item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class SinanewsDownloaderMiddleware(object):
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

setting.py中打开

ITEM_PIPELINES = {
   'sinanews.pipelines.SinanewsPipeline': 300,
}

并将遵循robotstxt协议注释，否则有些网站怕不下来

# ROBOTSTXT_OBEY = True

然后随机设置几个user-agent