19 03 13 关于 scrapy 框架的 对环球网的整体爬取(存储于 mongodb 数据库里)

关于  spinder  在这个框架里面   和不用数据库  相同 

# -*- coding: utf-8 -*-
import scrapy
from yang_guan.items import YangGuanItem
from copy import deepcopy
from scrapy.spiders import CrawlSpider

class YgSpider(scrapy.Spider):
    name = 'yg'
    allowed_domains = ['huanqiu.com']
    start_urls = ['http://www.huanqiu.com/',
                  ]

    def parse (self, response):  # 总页面  第一个一定要用parse  用来传递start_urls
        item = YangGuanItem()
        # item = {}

        class_news_urls_li = response.xpath(".//div[@class='navCon']/ul/li/a")
        print(class_news_urls_li)
        for class_news_url in class_news_urls_li:
            item["class_tittle"] = class_news_url.xpath("./text()").extract_first()
            print(item)
            new_url = class_news_url.xpath("./@href").extract_first()
            print(new_url)
            yield scrapy.Request(
                new_url,
                callback=self.second_class,
                meta={"item": deepcopy(item)},  # 由于是多线程 所以要用深拷贝进入item
            )

    def second_class(self, response):  # 二级页面
        item = response.meta["item"]
        print(response.url)

        second_urls = response.xpath(".//div/h2/em")

        for second_url in second_urls:

            secoond_news_url = second_url.xpath("./a/@href").extract_first()

            yield scrapy.Request(
                secoond_news_url,
                callback=self.parse_detail_analyze,
                meta={"item": deepcopy(item)}
            )

    def parse_detail_analyze(self, response):  # 进入第三成  总细节的抓取  http://china.huanqiu.com/leaders/'
        item = response.meta["item"]

        li_list = response.xpath("//ul[@class='listPicBox']/li")

        for li in li_list:
            # item = YangGuanItem()
            item["title"] = li.xpath("./h3/a/text()").extract_first()
            item["img_url"] = li.xpath("./a/img/@src").extract_first()
            item["detail"] = li.xpath("./h5/text()").extract_first()
            yield item

        next_url = response.xpath(".//div[@class='pageBox']/div/a[last()]/@href").extract_first()  # 遇见翻页就要这样写

        yield scrapy.Request(next_url, callback=self.parse_detail_analyze,meta={"item":response.meta["item"]})

关于  pipelines  的 管道设定

# -*- 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
import pymongo


class YangGuanPipeline(object):

    def __init__(self):
        # 建立mongodb 数据库连接
        client = pymongo.MongoClient('127.0.0.1', 27017)
        # 连接数据库,['scrapy_huan_qiu]
        db = client['scrapy_huan_qiu']
        # 连接所用的集合
        self.post = db['zong_huan_qiu']
        print("*"*100)

    def process_item(self, item, spider):
        postItem = dict(item)
        self.post.insert(postItem)
        return item

setting  的设置

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

# Scrapy settings for yang_guan 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

#  好像记得是ip代理
PROXIES = [
    {'ip_port': '111.11.228.75:80', 'user_pass': ''},
    {'ip_port': '120.198.243.22:80', 'user_pass': ''},
    {'ip_port': '111.8.60.9:8123', 'user_pass': ''},
    {'ip_port': '101.71.27.120:80', 'user_pass': ''},
    {'ip_port': '122.96.59.104:80', 'user_pass': ''},
    {'ip_port': '122.224.249.122:8088', 'user_pass': ''},]



BOT_NAME = 'yang_guan'

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

# LOG_LEVEL = "WARNING"

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# 计算机型号防止反爬虫
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'

# Obey robots.txt rules
# 不遵守爬虫机器人协议
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 = {
#    'yang_guan.middlewares.YangGuanSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'yang_guan.middlewares.YangGuanDownloaderMiddleware': 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

#  开启管道  由于这次没有编写 items  也无法保存进入数据库
ITEM_PIPELINES = {
   'yang_guan.pipelines.YangGuanPipeline': 300,
}

#  关于  debug等级  和生成log日志
# LOG_FILE = "dg.log"
# LOG_LEVEL = "DEBUG"


# 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'

关于item  的设置   这个一定要有  用spider 里面的 yield 来进行传递 字典

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

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

import scrapy


class YangGuanItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    class_tittle = scrapy.Field()
    img_url = scrapy.Field()
    detail = scrapy.Field()

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

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

import scrapy


class YangGuanItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    class_tittle = scrapy.Field()
    img_url = scrapy.Field()
    detail = scrapy.Field()

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

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

import scrapy


class YangGuanItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
    class_tittle = scrapy.Field()
    img_url = scrapy.Field()
    detail = scrapy.Field()