Python Scrapy 爬取煎蛋网妹子图实例（一）

原创

chinayyj2012 2021-09-26 16:08:18 博主文章分类：Python ©著作权

文章标签 html ide 数据库 xml .net 文章分类 代码人生

©著作权归作者所有：来自51CTO博客作者chinayyj2012的原创作品，请联系作者获取转载授权，否则将追究法律责任

前面介绍了爬虫框架的一个实例，那个比较简单，这里在介绍一个实例

爬取煎蛋网妹子图，遗憾的是上周煎蛋网还有妹子图了，但是这周妹子图变成了随手拍，

不过没关系，我们爬图的目的是为了加强实战应用，管他什么图了先爬下来再说。

言归正传

这个实例，主要是讲将图片爬了下来，保存到本地，这个在上周已经实现了，这周有进一步做了讲图片信息保存到了数据库中。

代码结构

Python Scrapy 爬取煎蛋网妹子图实例（一）_ide

如上图

common 用来存放共代码，如上篇对数据库的操作进行了封装，这里直接就放到了common 文件夹下，方便调用。

紧接着下面两个文件夹是用来存放爬取的图片的，第一个是这周爬的随手拍的图片，第二个是妹子图的图片。

然后下面就是爬虫文件了。

一下贴出对应文件的代码

JdwSpider.py

# -*- coding: utf-8 -*-
import base64


import scrapy

import JianDanW.items as items
from bs4 import BeautifulSoup


class JdwspiderSpider(scrapy.Spider):
    name = 'JdwSpider'
    allowed_domains = ['jandan.net']
    start_urls = ['http://jandan.net/ooxx/']

    # start_urls = ['http://jandan.net/ooxx/page-1#comments']



    def parse(self, response):

        item = items.JiandanwItem()

        # 通过 response.text 获取 html 源文件
        html = response.text

        # 使用 lxml 解析器解析 html 此时 soup 为 html 样式文件。
        soup = BeautifulSoup(html, 'lxml')
        # 查找 html 中的 img-hash 返回 包含 class="img-hash" 的 列表
        tags = soup.select('.img-hash')
        imgUrlList = []
        for tag in tags:
            #  tag  为 <span class="img-hash">Ly93eDQuc2luYWltZy5jbi9tdzYwMC82NmIzZGUxN2d5MWZ4bzZqaXM0aWVqMjFtYTB1MHg2ci5qcGc=</span>
            # img_hash = Ly93eDQuc2luYWltZy5jbi9tdzYwMC82NmIzZGUxN2d5MWZ4bzZqaXM0aWVqMjFtYTB1MHg2ci5qcGc=
            img_hash = tag.text
            # img_hash 进行解密 为 //wx4.sinaimg.cn/mw600/66b3de17gy1fxo6jis4iej21ma0u0x6r.jpg
            img_url = base64.b64decode(img_hash).decode('utf-8')
            # 将结果加载到列表
            imgUrlList.append(img_url)

        # print(img_urls)
        # 将列表复制给item 对应的 image_urls
        item['image_urls'] = imgUrlList

        yield item

        # 获取翻页 下一页 连接
        p_url = response.xpath('//a[@class="previous-comment-page"]//@href').extract_first()
        # 如果存在下一页
        if p_url:

            p_url = str(p_url)
            hurl = 'http:'
            page_url = hurl + p_url
            # 如果存在下一页，回调 parse 函数
            yield scrapy.Request(page_url,callback=self.parse)

items.py

# -*- 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 JiandanwItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    image_urls = scrapy.Field()#图片的链接

pipelines.py

# -*- 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 os
import urllib

import common.DBHandle as DBHandle

class JiandanwPipeline(object):
    def process_item(self, item, spider):

        # 数据库连接
        host = '127.0.0.1'
        username = 'adil'
        password = 'helloyyj'
        database = 'AdilTest'
        port = 3306
        DbHandle = DBHandle.DataBaseHandle(host, username, password, database, port)
        for image_url in item['image_urls']:
            # 截图图片链接
            list_name = image_url.split('/')
            # 获取图片名称
            file_name = list_name[len(list_name) - 1]  # 图片名称
            # 获取当前路径
            currentPath = os.getcwd()
            # 拼接图片存放路径
            file_path = os.path.join(currentPath,spider.name)
            # 如果图片路径不存在，创建该文件路径
            if not os.path.exists(file_path):
                os.makedirs(file_path)
            # 补全图片路径
            path_name = os.path.join(file_path,file_name)
            # 获取有效的url 因为 image_url = //wx4.sinaimg.cn/mw600/66b3de17gy1fxo6jis4iej21ma0u0x6r.jpg
            image_url = 'http:' + image_url
            # 此处执行 数据库插入，将 图片名称、url 插入到数据库   注意 这里的 values('占位符 一定要用 引号引起来，要不然执行不成功，血的教训')
            sql = "insert into JdwSpider(image_name,image_url) values ('%s','%s')" % (file_name,image_url)
            # 如果不执行插入，可以注释改该行代码
            DbHandle.insertDB(sql)

            # 图片保存
            with open(path_name, 'wb') as file_writer:
                conn = urllib.request.urlopen(image_url)  # 下载图片
                # 保存图片
                file_writer.write(conn.read())
            file_writer.close()
        # 关闭数据库
        DbHandle.closeDb()
        return item

配置 setting.py

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

# Scrapy settings for JianDanW 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

BOT_NAME = 'JianDanW'

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


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

# 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 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 = {
#    'JianDanW.middlewares.JiandanwSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'JianDanW.middlewares.JiandanwDownloaderMiddleware': 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
ITEM_PIPELINES = {
   'JianDanW.pipelines.JiandanwPipeline': 300,
}

# 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'