凤凰网分类爬虫

1. pycharm开发工具+python2.7+scrapy框架

2.项目开发

2.1 创建项目

scrapy startproject Ifeng

image.png

2.2 写自己需要的参数，在items文件里面写

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

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

import scrapy


class IfengdataItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 大类的标题 和 url
    parentTitle = scrapy.Field()
    parentUrls = scrapy.Field()

    # 小类的标题 和 子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()
    pass

2.2 在spider子目录下新建爬虫开始文件，我这里命名为ifeng.py

#coding=utf-8
import scrapy
from ifengdata.items import IfengdataItem
import os
class ifengdata(scrapy.Spider):
    name='ifeng'
    allowed_domains = ["ifeng.com"]
    start_urls = [
        "http://www.ifeng.com/daohang/"
    ]
    def parse(self, response):

        items=[]
        #所有的大标题和url
        parentUrls = response.xpath('//div[@class="col3"]/h2/a/@href').extract()
        parentTitle = response.xpath('//div[@class="col3"]/h2/a/text()').extract()

        # 所有小类的ur 和 标题
        subUrls = response.xpath('//div[@class="col3"]/div/div/div/div/ul/li/a/@href').extract()
        subTitle= response.xpath('//div[@class="col3"]/div/div/div/div/ul/li/a/text()').extract()
        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)
            for j in range(0,len(subTitle)):
                item = IfengdataItem()
                item['parentUrls']=parentUrls[i]
                item['parentTitle']=parentTitle[i]
                # yield item
                # 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)

    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
        # 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].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 = IfengdataItem()
                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=\"artical_topic\"]/text()').extract()
        content_list = response.xpath('//div[@id=\"main_content\"]/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
        if head!='':
            item['head'] = head[0]
            print(item['head'])
        else :
            item['head']=1
        item['content'] = content

        yield item

2.3配置管道pipelines.py

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

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

# import pymongo
import pymysql
from ifengdata import settings
class IfengdataPipeline(object):
    def __init__(self):
        # host='127.0.0.1'
        # port=27017
        # client=pymongo.MongoClient(host=host,port=port)
        # dbname = 'ifeng'
        #
        # # pymongo.MongoClient(host, port) 创建MongoDB链接
        # # 指向指定的数据库
        # mdb = client[dbname]
        # # 获取数据库里存放数据的表名
        # self.post = mdb['ifengdata1']
        # 获取setting主机名、端口号和数据库名
        # host = settings['MONGODB_HOST']
        # host='127.0.0.1'
        # port = settings['MONGODB_PORT']
        # port=27017
        # dbname = settings['MONGODB_DBNAME']
        # dbname='IFeng'
        # pymongo.MongoClient(host, port) 创建MongoDB链接
        # client = pymongo.MongoClient(host=host, port=port)
        # 指向指定的数据库
        # mdb = client[dbname]
        # 获取数据库里存放数据的表名
        # self.post = mdb[settings['MONGODB_DOCNAME']]
        # self.post= mdb['IFengData']
        self.conn = pymysql.connect(
            host='localhost',
            port=3306,
            user='root',
            password='root',
            db='test',
            charset='utf8',
        )
        self.cursor=self.conn.cursor()
    def process_item(self, item, spider):
        item = dict(item)
        sql = 'select * from ifengdata4 WHERE mulu=%s'
        par =[item['parentTitle']]
        name = self.cursor.execute(sql,par)
        self.conn.commit()
        if name:
            pass
        else:
            sql1='insert into ifengdata4(id,mulu) VALUES(null,%s)'
            params=[item['parentTitle']]
            self.cursor.execute(sql1,params)
            self.conn.commit()
        sql4 = 'select * from ifengdata5 WHERE zimulu=%s'
        par4 = [item['subTitle']]
        name = self.cursor.execute(sql4, par4)
        self.conn.commit()
        if name:
            pass
        else:
            sql2 = 'insert into ifengdata5(id,zimulu) VALUES(null,%s)'
            params2=[item['subTitle']]
            self.cursor.execute(sql2, params2)
            self.conn.commit()
        sql3 = 'insert into ifengdata6(id,title) VALUES(null,%s)'
        params3 = [item['head']]
        self.cursor.execute(sql3, params3)
        self.conn.commit()
        return item

2.4设置settings.py文件

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

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

BOT_NAME = 'ifengdata'

SPIDER_MODULES = ['ifengdata.spiders']
NEWSPIDER_MODULE = 'ifengdata.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'ifengdata (+http://www.yourdomain.com)'
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True

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

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'ifengdata.middlewares.IfengdataSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'ifengdata.middlewares.MyCustomDownloaderMiddleware': 543,
#}

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

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'ifengdata.pipelines.IfengdataPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://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 http://scrapy.readthedocs.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'
# MONGODB 主机环回地址127.0.0.1
# MONGODB_HOST = '127.0.0.1'
# 端口号，默认是27017
# MONGODB_PORT = 27017
# 设置数据库名称
# MONGODB_DBNAME = 'IFeng'
# 存放本次数据的表名称
# MONGODB_DOCNAME = 'IFengData'

DOWNLOAD_DELAY = 1

REDIS_HOST = "192.168.13.23"
REDIS_PORT = 6379

可以试一下哦，有问题请留言