项目结构:
qsbk_scrapy_selenium.py
# -*- coding: utf-8 -*-
import scrapy
from pydispatch import dispatcher
from scrapy import signals
from selenium import webdriver
from scrapy_selenium.items import ScrapySeleniumItem
class QsbkScrapySeleniumSpider(scrapy.Spider):
name = 'qsbk_scrapy_selenium'
allowed_domains = ['qiushibaike.com']
start_urls = ['https://www.qiushibaike.com/text/page/1/']
crawl_domain = 'https://www.qiushibaike.com'
def __init__(self):
self.browser = webdriver.Chrome()
#调用父类构造函数
super(QsbkScrapySeleniumSpider, self).__init__()
dispatcher.connect(self.spider_closed, signals.spider_closed)
def spider_closed(self):
print("spider closed")
#爬虫关闭时关闭浏览器
self.browser.quit()
def parse(self, response):
print("=" * 40)
# <class 'scrapy.http.response.html.HtmlResponse'>
print(type(response))
print("=" * 40)
# xpath方式解析元素
hrefList = response.xpath("//div[@id='content']//a[@class='contentHerf']/@href").getall()
for href in hrefList:
print(self.crawl_domain + href)
yield scrapy.Request(self.crawl_domain + href, callback=self.getContent)
next_url = response.xpath("//ul[@class='pagination']/li[last()]/a/@href").get()
if not next_url:
# 程序结束
return
else:
# 发送下一页请求
yield scrapy.Request(self.crawl_domain + next_url, callback=self.parse)
def getContent(self, response):
content = response.xpath("//div[@id='content']//div[@class='content']/text()").getall()
print(content)
# 将数据放入一个对象里面
item = ScrapySeleniumItem(duanzi=content)
# 将数据返回给管道
yield item
items.py
import scrapy
class ScrapySeleniumItem(scrapy.Item):
duanzi = scrapy.Field()
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 time import sleep
from pydispatch import dispatcher
from scrapy import signals
from scrapy.http import HtmlResponse
#爬虫中间件
class ScrapySeleniumSpiderMiddleware(object):
# 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)
#下载器中间件
class ScrapySeleniumDownloaderMiddleware(object):
# 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
#可以在请求下载器之前做一些设置
def process_request(self, request, spider):
if spider.name == 'qsbk_scrapy_selenium':
#同步请求
spider.browser.get(request.url)
sleep(3)
print("访问url:" + request.url)
#url:请求路径 body:请求返回的资源
return HtmlResponse(url=spider.browser.current_url, body=spider.browser.page_source,
encoding='utf8', request=request)
#可以在返回引擎之前做一些设置
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)
pipelines.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
import json
#存储数据
class ScrapySeleniumPipeline(object):
def __init__(self):
self.fp = open("duanzi.json", "w", encoding="utf-8")
def open_spider(self, spider):
print("爬虫开始了...")
def process_item(self, item, spider):
# 接收parse函数返回的数据
item_json = json.dumps(dict(item), ensure_ascii=False)
# \n代表换行
self.fp.write(item_json + "\n")
return item
def close_spider(self, spider):
self.fp.close()
print("爬虫结束了...")
settings.py
# -*- coding: utf-8 -*-
# Scrapy settings for scrapy_selenium 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 = 'scrapy_selenium'
SPIDER_MODULES = ['scrapy_selenium.spiders']
NEWSPIDER_MODULE = 'scrapy_selenium.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'scrapy_selenium (+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 https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 1
# 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:
#设置请求头
DEFAULT_REQUEST_HEADERS = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en',
'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'
}
# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'scrapy_selenium.middlewares.ScrapySeleniumSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#打开下载器
DOWNLOADER_MIDDLEWARES = {
'scrapy_selenium.middlewares.ScrapySeleniumDownloaderMiddleware': 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 = {
'scrapy_selenium.pipelines.ScrapySeleniumPipeline': 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'
startCrawlProject.py
from scrapy import cmdline
#直接运行这个文件 不需要在命令行敲scrapy crawl qsbk_spider代码
cmdline.execute(['scrapy','crawl','qsbk_scrapy_selenium'])