爬取伯乐在线文章中的封面图并保存在本地

首先还是和以往一样，分析页面源代码。不再说具体过程。图片保存在本地，所以要新建一个文件夹images

同时也要修改settings中的内容。最好使用相对路径来保存，这样子代码移植到别的机器上无需修改路径就可以直接运行。这就需要用到os模块。具体代码如下。

整个过程代码如下。

Jobbole.py

# -*- coding: utf-8 -*-
import scrapy
import re
from scrapy.http import Request
from urllib import parse
from ArticleSpider.items import JobBoleArticleItem
class JobboleSpider(scrapy.Spider):
    name = 'jobbole'
    allowed_domains = ['blog.jobbole.com']
    start_urls = ['http://blog.jobbole.com/all-posts/']

    def parse(self, response):

      #1.获取文章列表页中的url并交给scrapy下载后进行解析
      #2.获取下一页的url并交给scrapy进行下载，下载完成后交给parse
      #解析列表页中的所有文章url交给scrapy下载后进行解析
        post_nodes = response.css("#archive .floated-thumb .post-thumb a")
        for post_node in post_nodes:
            image_url = post_node.css("img::attr(src)").extract_first("")
            post_url = post_node.css("::attr(href)").extract_first("")
            yield Request(url=parse.urljoin(response.url,post_url),meta={"front_image_url":image_url},callback=self.parse_detail)
        #提取下一页并交给scrapy进行下载
        next_url = response.css(".next.page-numbers::attr(href)").extract_first("")
        if next_url:
            yield Request(url=parse.urljoin(response.url, next_url), callback=self.parse)
    def parse_detail(self, response):
        article_item = JobBoleArticleItem()
    #通过CSS选择器提取文章具体字段
        front_image_url = response.meta.get("front_image_url","")#文章封面图
        title = response.css(".entry-header h1::text").extract()[0]
        create_date = response.css(".entry-meta-hide-on-mobile::text").extract()[0].strip().replace("·","").strip()
        praise_numbers = response.css(".vote-post-up h10::text").extract()[0]
        fav_nums = response.css("span.bookmark-btn::text").extract()[0]
        match_re = re.match(".*?(\d+).*", fav_nums)
        if match_re:
            fav_nums = int(match_re.group(1))
        else:
            fav_nums = 0
        comment_nums = response.css("a[href='#article-comment'] span::text").extract()[0]
        match_re = re.match(".*?(\d+).*", comment_nums)
        if match_re:
            comment_nums = int(match_re.group(1))
        else:
            comment_nums = 0
        content = response.css("div.entry").extract()[0]
        tags = response.css("p.entry-meta-hide-on-mobile a::text").extract()[0]

        article_item["title"] = title
        article_item["url"] = response.url
        article_item["create_date"] = create_date
        article_item["comment_nums"] = comment_nums
        article_item["content"] = content
        article_item["tags"] = tags
        article_item["praise_numbers"] = praise_numbers
        article_item["fav_nums"] = fav_nums
        article_item["front_image_url"] = [front_image_url]
        yield article_item

settings.py

# -*- coding: utf-8 -*-
import os
# Scrapy settings for ArticleSpider 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 = 'ArticleSpider'

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


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

# Obey robots.txt rules
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 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 = {
ITEM_PIPELINES = {
    'ArticleSpider.middlewares.ArticlespiderSpiderMiddleware': 543,
    'scrapy.pipelines.images.ImagesPipeline':1,
}
IMAGES_URLS_FIELD = "front_image_url"
project_dir = os.path.abspath(os.path.dirname(__file__))
IMAGES_STORE = os.path.join(project_dir,'images')

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'ArticleSpider.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 = {
#    'ArticleSpider.pipelines.ArticlespiderPipeline': 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'

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


class ArticlespiderItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    pass
class JobBoleArticleItem(scrapy.Item):
    url = scrapy.Field()
    url_object_id = scrapy.Field()
    title = scrapy.Field()
    create_date = scrapy.Field()
    praise_numbers = scrapy.Field()
    fav_nums = scrapy.Field()
    comment_nums = scrapy.Field()
    content = scrapy.Field()
    tags = scrapy.Field()
    front_image_url = scrapy.Field()
    front_image_path = scrapy.Field()

main.py

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

from scrapy.cmdline import execute

import sys
import os

sys.path.append(os.path.dirname(os.path.abspath(__file__)))
execute(["scrapy","crawl","jobbole"])

直接运行main.py,就下载了伯乐在线的所有封面图，并保存在images中。如图所示