最网最全python框架--scrapy（体系学习，爬取全站校花图片），学完显著提高爬虫能力（附源代码），突破各种反爬

Posted 2021-05-21 yk 坤帝

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了最网最全python框架--scrapy（体系学习，爬取全站校花图片），学完显著提高爬虫能力（附源代码），突破各种反爬相关的知识，希望对你有一定的参考价值。

个人公众号 yk 坤帝
后台回复scrapy 获取全部源代码

1.boss直聘爬虫（bossPro）

2.豆瓣爬虫（db）

3.fbsPro

4.百度爬虫（firstblood）

5.校花全站图片爬虫（imgsPro）

6.代理ip配置爬虫（middlePro）

7.全站视频爬虫（moviePro）

8.糗图百科视频，图片，视频下载（qiubaiPro）

9.最新问政-阳光热线问政平台–相关政策全站爬虫（sunPro）

10.网易新闻全站信息爬虫（wangyiPro）

11.中国校花网，全站校花图片爬取（xiaohuaPro）

12.数据库示例

在这里插入图片描述

1.boss直聘爬虫（bossPro）
在这里插入图片描述

boss.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月23日星期二
# 寒假开学开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy
from bossPro.items import BossproItem


class BossSpider(scrapy.Spider):
    name = 'boss'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.zhipin.com/c101010100/?query=python&ka=sel-city-101010100']

    url = 'https://www.zhipin.com/job_detail/bd1e60815ee5d3741nV92Nu1GVZY.html?ka=search_list_jname_1_blank&lid=8iXPDpH593w.search.%d'
    page_num = 2

    def parse_detail(self,response):
        item = response.meta['item']

        job_desc = response.xpath('//*[@id="main"]/div[3]/div/div[2]/div[2]/div[1]/div//text()').extract()
        job_desc = ''.join(job_desc)
        item['job_desc'] = job_desc
        print(job_desc)

        yield item

    def parse(self, response):

        li_list = response.xpath('//*[@id="main"]/div/div[2]/ul/li')
        print(li_list)
        for li in li_list:
            item = BossproItem()

            job_name = li.xpath('.//span[@class="job-name"]a/text()').extract_first()
            item['job_name'] = job_name
            print(job_name)
            detail_url ='https://www.zhipin.com/' + li.xpath('.//span[@class="job-name"]a/@href').extract_first()

            yield scrapy.Request(detail_url,callback=self.parse_detail,meta={'item':item})

        if self.page_num <=3:
            new_url = format(self.url%self.page_num)   
            self.page_num += 1

            yield scrapy.Request(new_url,callback = self.parse)

items.py

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

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

import scrapy


class BossproItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    job_name = scrapy.Field()
    job_desc = scrapy.Field()
    #pass

middlewares.py

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

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

from scrapy import signals


class BossproSpiderMiddleware:
    # 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 Request, 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 BossproDownloaderMiddleware:
    # 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)

piplelines.py

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

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


class BossproPipeline:
    def process_item(self, item, spider):
        print(item)
        return item

settings.py

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

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

BOT_NAME = 'bossPro'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.193 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False
LOG_LEVEL = 'ERROR'

# 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://docs.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://docs.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
#    'bossPro.middlewares.BossproSpiderMiddleware': 543,
# }

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'bossPro.middlewares.BossproDownloaderMiddleware': 543,
#}

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

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'bossPro.pipelines.BossproPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.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://docs.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'

2.豆瓣爬虫（db）
在这里插入图片描述

db.py

# 大二
# 2021年3月4日
# 寒假开学时间3月7日
# -*- coding: utf-8 -*-
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码


import scrapy


class DbSpider(scrapy.Spider):
    name = 'db'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.douban.com/group/topic/157797102/']

    def parse(self, response):
        li_list = response.xpath('//*[@id="comments"]/li')
        # print(li_list)
        for li in li_list:
            # print(li)
            #/html/body/div[3]/div[1]/div/div[1]/ul[2]/li[1]/div[2]/p
            comments = li.xpath('./div[2]/p/text()').extract_first()
            print(comments)

3.fbsPro

# -*- coding: utf-8 -*-
# 大二
# 2021年2月24日星期三
# 寒假开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

from scrapy_redis.spiders import RedisCrawlSpider
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from fbsPro.items import FbsproItem


class FbsSpider(RedisCrawlSpider):
    name = 'fbs'
    #allowed_domains = ['www.xxx.com']
    #start_urls = ['http://www.xxx.com/']
    redis_key = 'sun'

    rules = (
        Rule(LinkExtractor(allow=r'Items/'), callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        item = {}
        #item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
        #item['name'] = response.xpath('//div[@id="name"]').get()
        #item['description'] = response.xpath('//div[@id="description"]').get()
        item = FbsproItem()

        yield item

4.百度爬虫（firstblood）
first.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月19日星期五
# 寒假开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy


class FirstSpider(scrapy.Spider):
    name = 'first'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.baidu.com/','https://www.sogou.com']


    def parse(self, response):
        print(response)

5.校花全站图片爬虫（imgsPro）
在这里插入图片描述

img.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月23日星期二
# 寒假开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy
from imgsPro.items import ImgsproItem


class ImgSpider(scrapy.Spider):
    name = 'img'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['https://sc.chinaz.com/tupian/']

    def parse(self, response):
        div_list = response.xpath('//div[@id="container"]/div')
        for div in div_list:
            src ='https:' + div.xpath('./div/a/img/@src2').extract_first()
            print(src)

            item = ImgsproItem()
            item['src'] = src

            yield item

6.代理ip配置爬虫（middlePro）
在这里插入图片描述
middle.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月23日
# 寒假开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy


class MiddleSpider(scrapy.Spider):
    name = 'middle'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://www.baidu.com/s?wd=ip']

    def parse(self, response):
        page_text = response.text 

        with open('ip.html','w',encoding= 'utf-8') as fp:
            fp.write(page_text)

7.全站视频爬虫（moviePro）
在这里插入图片描述

movie.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月24日星期三
# 寒假开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from moviePro.items import MovieproItem
from redis import Redis


class MovieSpider(CrawlSpider):
    name = 'movie'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://www.4567kan.com/frim/index1.html']

    rules = (
        Rule(LinkExtractor(allow=r'/frim/index1-\\d+\\.html'), callback='parse_item', follow=True),
    )
    conn = Redis(host = '127.0.0.1', port = 6379)

    def parse_item(self, response):
        li_list = response.xpath('/html/body/div[1]/div/div/div/div[2]/ul/li')
        for li in li_list:

            detail_url = 'http://www.4567kan.com/' + li.xpath('./div/a/@href').extract_first()

            ex = self.conn.sadd('urls',detail_url)

            if ex == 1:

                print('该url没有被爬取过，可以进行数据的爬取')
                yield scrapy.Request(url = detail_url, callback= self.parst_detail)

            else:

                print('数据还没有更新，暂无新数据可爬！')

    def parst_detail(self,response):

        item = MovieproItem()
        item['name'] = response.xpath('/html/body/div[1]/div/div/div/div[2]/h1/text()').extract_first()
        item['desc'] = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[5]/span[2]//text()').extract()
        item['desc'] = ''.join(item['desc'])
        yield item

8.糗图百科视频，图片，视频下载（qiubaiPro）
在这里插入图片描述 qiubai.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月19日星期五
# 寒假开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy
from qiubaiPro.items import QiubaiproItem

class QiubaiSpider(scrapy.Spider):
    name = 'qiubai'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.qiushibaike.com/text/']
    

#     def parse(self, response):
#         div_list = response.xpath('//div[@id="content"]/div[1]/div[2]/div')
#         all_data = []
#         for div in div_list:
#             auther = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
#             #auther = div.xpath('./div[1]/a[2]/h2/text()').extract_first()
#             content = div.xpath('./a[1]/div/span//text()').extract()
#             content = ','.join(content)
#             print(auther,content)
#             dic = {
#                 auther:'auther',
#                 content:'auther'
#             }
#             all_data.append(dic)

#         return all_data

# 大二
# 2021年2月21日星期日
# 寒假开学时间3月7日
    def parse(self, response):
        div_list = response.xpath('//div[@id="content"]/div[1]/div[2]/div')
        
        #all_data = []
        for div in div_list:
            auther = div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
            #匿名用户
            #auther = div.xpath('./div[1]/a[2]/h2/text() | ./div[1]/span/h2/text()')[0].extract()
            #auther = div.xpath('./div[1]/a[2]/h2/text()').extract_first()
            content = div.xpath('./a[1]/div/span//text()').extract()
            content = ','.join(content)

            item = QiubaiproItem()
            item['auther'] = auther
            item['content'] = content

            yield item

9.最新问政-阳光热线问政平台–相关政策全站爬虫（sunPro）
在这里插入图片描述
sun.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月24日星期三
# 寒假开学时间3月7日
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule


class SunSpider(CrawlSpider):
    name = 'sun'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://wz.sun0769.com/political/index/politicsNewest?id=1&page=1']

    link = LinkExtractor(allow=r'id=1&page=\\d+')
    rules = (
        Rule(link, callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        print(response)

10.网易新闻全站信息爬虫（wangyiPro）
在这里插入图片描述
wangyi.py

# -*- coding: utf-8 -*-
# 大二
# 2021年2月23日星期二
# 寒假开学时间3月7号
# 个人公众号 yk 坤帝
# 后台回复scrapy 获取全部源代码

import scrapy

from wangyiPro.items import WangyiproItem
from selenium import webdriver
class WangyiSpider(scrapy.Spider):
    name = 'wangyi'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['https://news.163.com/']

    models_urls = []

    def __init__(self):
        self.bro = webdriver.Chrome()

    def parse(self, response):
        li_list = response.xpath('//*[@id="js_festival_wrap"]/div[3]/div[2]/div[2]/div[2]/div/ul/li')
        alist = [3,4,6,7,8]
        for index in alist:
            model_url = li_list[index].xpath('./a/@href').extract_first()
            self.models_urls.append(model_url)

        for url in self.models_urls:
            yield scrapy.Request(url,callback= self.parse_model)

    def parse_model(self,response):
        
        div_list = response.xpath('/html/body/div[1]/div[3]/div[4]/div[1]/div/div/ul/li/div/div')

        for div in div_list:
            title = div.xpath('./div/div[1]/h3/a/text()').extract_first()
            new_detail_url = div.xpath('./div/div[1]/h3以上是关于最网最全python框架--scrapy（体系学习，爬取全站校花图片），学完显著提高爬虫能力（附源代码），突破各种反爬的主要内容，如果未能解决你的问题，请参考以下文章 
 第三篇：爬虫框架 - Scrapy
 18分钟带你掌握商业爬虫框架Scrapy---爬取明星图片
 全网最全python爬虫精进（体系学习）学完可就业（附源代码）
 python 爬虫框架scrapy学习记录和整理 python爬虫框架scrapy入门文档学习
 Python学习---爬虫学习[scrapy框架初识]
 python应用：爬虫框架Scrapy系统学习第二篇——windows下安装scrapy