CrawlSpider深度爬取
CrawlSpider是什么:
crawlspider也是一个spider,是spider的一个子类,所以其功能要比Spider要强大。
多的功能是:提取链接的功能,根据一定的规则,提取指定的链接。
链接提取器:
LinkExtractor(
allow = xxx, # 正则表达式,要(*)
deny = xxx, # 正则表达式,不要这个
restrict_xpaths = xxx, # xpath路径(*)
restrict_css = xxx, # 选择器(*)
deny_domains = xxx, # 不允许的域名
)
项目截图:
运行命令:
- scrapy startproject news
- cd news
- scrapy genspider -t crawl qiubai www.qiushibaike.com
示例代码:
items.py文件中:
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class NewsItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
# 用户头像的url地址
icon_url = scrapy.Field()
# 用户名
username = scrapy.Field()
# 用户年龄
age = scrapy.Field()
# 用户发表的内容
content = scrapy.Field()
# 好笑的个数
haha_count = scrapy.Field()
# 评论数量
coment_count = scrapy.Field()
settings.py文件:
# Scrapy settings for news 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 = 'news'
LOG_LEVEL = 'ERROR'
SPIDER_MODULES = ['news.spiders']
NEWSPIDER_MODULE = 'news.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = '改为自己的User-Agent'
# 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 https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.6
# 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 = {
# 'news.middlewares.NewsSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'news.middlewares.NewsDownloaderMiddleware': 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 = {
'news.pipelines.NewsPipeline': 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'
piplines.py文件中:
# 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
# useful for handling different item types with a single interface
import json
from itemadapter import ItemAdapter
class NewsPipeline:
# 重写这个方法,当爬虫开启的时候就会调用这个方法
def open_spider(self, spider):
self.fp = open('qiubai.txt', 'w', encoding='utf8')
# 处理item数据的方法
def process_item(self, item, spider):
# 要将item保存到文件中
# 将对象转化为字典
dic = dict(item)
# 将字典转化为json数据
strin = json.dumps(dic, ensure_ascii=False)
self.fp.write(strin + '\n')
return item
# 当爬虫结束时候调用这个方法
def close_spider(self, spider):
self.fp.close()
qiubai.py文件中:
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from news.items import NewsItem
class QiubaiSpider(CrawlSpider):
name = 'qiubai'
# allowed_domains = ['www.qiushibaike.com']
start_urls = ['https://www.qiushibaike.com/text/']
# 根据规则提取链接
rules = (
# Rule(LinkExtractor(allow=r''), callback='parse_item', follow=True)如果是这样,会提取起始url这个页面以下的所有链接
Rule(LinkExtractor(allow=r'/text/page/\d+/'), callback='parse_item', follow=True),
)
def parse_item(self, response):
#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()
content_div = response.xpath('//*[@id="content"]/div/div[2]/div')
for content_d in content_div:
item = NewsItem()
# 头像的url地址
icon_url = content_d.xpath('.//div/a/img/@src').extract_first()
icon_url = 'https:' + icon_url
# 用户名
username = content_d.xpath('.//div/a[2]/h2/text()').extract_first().strip('\n')
# 年龄
age = content_d.xpath('.//div/div/text()').extract_first()
# 内容 //*[@id="qiushi_tag_124466562"]/a[1]/div/span/text()[2]
content = content_d.xpath('.//a[1]/div[@class="content"]/span[1]').xpath('string(.)').extract_first()
# 好笑个数
haha_count = content_d.xpath('.//div[2]/span[1]/i/text()').extract_first()
# 评论个数
comment_count = content_d.xpath('.//div[2]/span[2]/a/i/text()').extract_first()
item['icon_url'] = icon_url
item['username'] = username
item['age'] = age
item['content'] = content.strip('\n')
item['haha_count'] = haha_count
item['coment_count'] = comment_count
yield item
链接提取器不管用什么方式提取链接,都会把重复的链接自动去重。在scrapy shell中,可以这样:
link = LinkExtractor(allow=r'/text/page/\d+/')
link.extract_links(response) # 进行查看提取的链接
注意:
- 一个链接提取器对应一个规则解析器,多个链接提取器对应多个规则解析器。
link1 = LinkExtractor(allow=r'/text/page/\d+/')
link2 = LinkExtractor(allow=r'/text/page/\d+/')
rules = (
Rule(link1, callback='parse_item', follow=True)
Rule(link2, callback='parse_item', follow=True),
)
- 在实现深度爬取的过程中需要和scrapy.Request()结合使用。