欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

(77)--用框架爬取博客园信息并保存到数据库

程序员文章站 2022-07-12 20:50:45
...

# 用框架爬取博客园信息并保存到数据库

# cnlogs_itload.py

# -*- coding: utf-8 -*-
import scrapy
import re
from ..items import CnblogItem,CnblogItemLoader
from datetime import datetime
from w3lib.html import  remove_tags
from urllib import request

# scrapy url去重 (指纹过滤)
# url_id = {url1,url2}
# task_q = Queue(r1,r2)

# itemloader
# ['发布与 :2013-9-8'] -》输入管理器 ['2013-9-8'] - > 输出管理器 '2013-9-8' - > 赋值给item

class CnblogSpider(scrapy.Spider):
    name = 'cnblog_itemloader'
    allowed_domains = ['cnblogs.com']

    # 只针对cnblogspider 生效的配置
    custom_settings = {
        'ROBOTSTXT_OBEY' : False,
        'CONCURRENT_REQUESTS' : 100,
        'ITEM_PIPELINES' : {
            'day13.pipelines.CnblogPipeline': 1,
        }
    }

    headers = {
        "Host": "www.cnblogs.com",
        "Connection": "keep-alive",
        "X-Requested-With": "XMLHttpRequest",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36",
        "Content-Type": "application/json; charset=UTF-8",
        "Accept-Language": "zh-CN,zh;q=0.9",
    }

    # 构建首次请求
    def start_requests(self):
        base_url = 'https://www.cnblogs.com/aggsite/SubCategories'
        body = '{"cateIds":"108698,2,108701,108703,108704,108705,108709,108712,108724,4"}'

        yield scrapy.Request(base_url,method='post',headers=self.headers,body=body,callback=self.parse)

    def parse(self, response):
        cate_list = response.xpath('//a/@href').extract()
        for url in cate_list:
            url = request.urljoin(response.url,url)
            yield scrapy.Request(url,callback=self.parse_first,meta={'url' : url})

    # 解析所有分类第一页
    def parse_first(self,response):
        url = response.meta['url'] + '%d'
        try:
            max_page = response.xpath('//div[@class="pager"]/a/text()').extract()[-2]
            max_page = int(max_page)
        except Exception as e:
            max_page = 1

        for i in range(max_page,0,-1):
            fullurl = url % i
            yield scrapy.Request(fullurl,callback=self.parse_list)

    def parse_list(self,response):
        article_list = response.xpath('//div[@class="post_item"]')

        for article in article_list:
            # 创建数据模型
            item = CnblogItem()
            itemloader = CnblogItemLoader(item=item,selector=article)

            itemloader.add_css('title','h3 a::text')
            itemloader.add_css('article_link','h3 a::attr(href)')
            itemloader.add_css('re_num','span.diggnum::text')
            itemloader.add_css('industry','p.post_item_summary::text')
            itemloader.add_css('author','div.post_item_foot a::text')
            itemloader.add_css('date_pub','div.post_item_foot::text')
            itemloader.add_css('comment','span.article_comment a::text')
            itemloader.add_css('read_num','span.article_view a::text')
            itemloader.add_value('crawl_time',datetime.now().strftime('%Y-%m-%d'))
            itemloader.add_value('spider_name',self.name)

            # print(itemloader.load_item())
            # 详情页请求
            article_link = article.css('h3 a::attr(href)').extract_first()
            yield scrapy.Request(article_link,callback=self.parse_detail,meta={'data':itemloader})

    def parse_detail(self,response):
        itemloader = response.meta['data']
        itemloader.selector = response
        itemloader.add_xpath('content','//div[@id="post_detail"]')

        # print(itemloader.load_item())
        yield itemloader.load_item()

# items.py

# -*- 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
from scrapy.loader import ItemLoader
from scrapy.loader.processors import TakeFirst,Join,MapCompose
import re
from w3lib.html import remove_tags

class CnblogItemLoader(ItemLoader):
    default_output_processor = TakeFirst()

# 定义输入管理器
def v_format(value):
    # 数据已经被exetract
    for item in value:
        item.strip()
    return value

def process_date(date_pub):
    # 处理时间
    date_pub[0] = date_pub[-1].strip('\r\n ').strip('发布于 ')
    return date_pub

def get_num(value):
    num_pat = re.compile('\d+')
    res = num_pat.search(value[0])
    if res is not None:
        data = int(res.group())
    else:
        data = 0
    value[0] = data
    return value

def process_content(value):
    value[0] = remove_tags(value[0]).strip()
    return value

def process_title(value):
    value.append('_Alice')
    return value

class CnblogItem(scrapy.Item):
    title = scrapy.Field(
        input_processor = process_title,
        output_processor = Join('$')
    )
    content = scrapy.Field(
        input_processor = process_content
    )
    article_link = scrapy.Field()
    re_num = scrapy.Field()
    industry = scrapy.Field(
        input_processor = v_format,
    )
    author = scrapy.Field()
    date_pub = scrapy.Field(
        input_processor = process_date
    )
    comment = scrapy.Field(
        input_processor = get_num
    )
    read_num = scrapy.Field(
        input_processor=get_num
    )
    crawl_time = scrapy.Field()
    spider_name = scrapy.Field()

    def get_sql(self):
        sql = 'insert into py07_cnblog(title,content,article_link,re_num,industry,author,date_pub,comment,read_num,crawl_time,spider_name) ' \
              'values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)'
        data = (self["title"],self["content"],self["article_link"],self["re_num"],self["industry"],self["author"],self["date_pub"],self["comment"],self["read_num"],self["crawl_time"],self["spider_name"])
        return sql,data

# 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 pymysql

class Day13Pipeline(object):
    def process_item(self, item, spider):
        return item

class CnblogPipeline(object):
    def __init__(self):
        self.conn = pymysql.connect('127.0.0.1','root','123456','han',charset='utf8')
        self.cursor = self.conn.cursor()

    def process_item(self,item,spider):
        # 插入数据库
        sql ,data = item.get_sql()
        self.cursor.execute(sql,data)
        self.conn.commit()

        return item

    def close_spider(self,spider):
        self.cursor.close()
        self.conn.close()

# settings.py

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

# Scrapy settings for day13 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 = 'day13'

SPIDER_MODULES = ['day13.spiders']
NEWSPIDER_MODULE = 'day13.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'day13 (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 1

# 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 = {
#    'day13.middlewares.Day13SpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'day13.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 = {
#    'day13.pipelines.CnblogPipeline': 1,
# }

# 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'

# main.py

from scrapy import cmdline

# cmdline.execute('scrapy crawl cnblog'.split())
# cmdline.execute('scrapy crawl cnblog_all'.split())
cmdline.execute('scrapy crawl cnblog_itemloader'.split())


# 爬取部分结果如下:


(77)--用框架爬取博客园信息并保存到数据库


(77)--用框架爬取博客园信息并保存到数据库


兄弟连学python


Python学习交流、资源共享群:563626388 QQ



相关标签: 博客园