scrapy简书整站爬取
- 数据同步及异步存储到MySQL
- 对于ajax 加载的数据用selenium辅助加载解析
- 整站爬取提取url规则
使用了scrapy 提供的 crawlspider 提取规则的url列表，scrapy会自动帮我们提取。
jianshu.py 文件
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from jianshu_spider.items import JianshuSpiderItem
class JianshuSpider(CrawlSpider):
name = 'jianshu'
allowed_domains = ['jianshu.com']
start_urls = ['https://www.jianshu.com/']
rules = (
# 观察url发现，前缀都一样，后面是12个数字加小写字母的组合
Rule(LinkExtractor(allow=r'.*/p/[0-9a-z]{12}.*'), callback='parse_detial', follow=True),
)
def parse_detial(self, response):
title = response.xpath('//h1[@class="title"]/text()').extract_first('') # 提取标题
avatar = response.xpath('//a[@class="avatar"]/img/@src').extract_first('') # 提取头像
author = response.xpath('//span[@class="name"]/a/text()').extract_first('') # 提取作者
publish_time = response.xpath('//span[@class="publish-time"]/text()').extract_first('') # 提取发布时间
content = response.xpath('//div[@class="show-content"]').get() # 提取文章内容
# 提取文章ip,也就是url上面的不一样的字符串
process_url = response.url.split('?')[0] # 以问号分割取前一部分
article_id = process_url.split('/')[-1] # 以 ‘/’ 分割获取最后一个字符串即为文章的id
origin_url = response.url
print(title)
item = JianshuSpiderItem(title=title,avatar=avatar,author=author,publish_time=publish_time,
content=content,article_id=article_id,origin_url=origin_url)
return item
item.py文件
这里主要定义了一些要爬取的字段。还可以扩展爬取更多的字段。
class JianshuSpiderItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
avatar = scrapy.Field()
author = scrapy.Field()
publish_time = scrapy.Field()
content = scrapy.Field()
article_id = scrapy.Field()
origin_url = scrapy.Field()
settings.py文件
这里主要是一些设置的文件，包括请求头，打开pipelines,middleware.
ROBOTSTXT_OBEY = False
DOWNLOAD_DELAY = 1
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 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
DOWNLOADER_MIDDLEWARES = {
#'jianshu_spider.middlewares.JianshuSpiderDownloaderMiddleware': 543,
'jianshu_spider.middlewares.SeleniumDownloadMiddleware': 543,
}
ITEM_PIPELINES = {
'jianshu_spider.pipelines.JianshuSpiderPipeline': 300,
#'jianshu_spider.pipelines.JianshuTwistedPipeline': 300,
}
pipelines.py文件
这里把数据存储到数据库中。同步和异步两种方式。
import pymysql
from twisted.enterprise import adbapi # 使用异步数据库处理连接池
from pymysql import cursors # 数据库游标类
class JianshuSpiderPipeline(object):
def __init__(self):
params = {
'host':'127.0.0.1',
'port':3306,
'user':'root',
'password':'1326628437',
'database':'jianshu',
'charset':'utf8'
}
self.conn = pymysql.connect(**params)
self.sursor = self.conn.cursor()
self._sql = None
@property # 属性操作，可直接调用
def sql(self):
if not self._sql:
self._sql = '''insert into article(title,author,avatar,publish_time,article_id,
origin_url,content) value(%s,%s,%s,%s,%s,%s,%s)'''
return self._sql
return self._sql
def process_item(self, item, spider):
self.sursor.execute(self.sql,(item['title'],item['author'],item['avatar'],item['publish_time'],
item['article_id'],item['origin_url'],item['content']))
self.conn.commit()
return item
# 异步实现插入数据库，插入操作是io操作，数据量大时，会出现堵塞，异步插入很有必要
class JianshuTwistedPipeline(object):
def __init__(self):
params = {
'host':'127.0.0.1',
'port':3306,
'user':'root',
'password':'1326628437',
'database':'jianshu',
'charset':'utf8',
'cursorclass':cursors.DictCursor
}
# 调用异步连接池实现异步插入数据库
self.dbpool = adbapi.ConnectionPool("pymysql",**params)
self._sql = None
@property
def sql(self):
if not self._sql:
self._sql = '''insert into article(title,author,avatar,publish_time,article_id,
origin_url,content) value(%s,%s,%s,%s,%s,%s,%s)'''
return self._sql
return self._sql
def process_item(self,item,spider):
# 异步插入数据
defer = self.dbpool.runInteraction(self.insert_item,item)
# 错误处理
defer.addErrback(self.handle_error,item,spider)
def insert_item(self,item,cursor):
cursor.execute(self.sql,(item['title'],item['author'],item['avatar'],item['publish_time'],
item['article_id'],item['origin_url'],item['content']))
def handle_error(self,item,error,spider):
print('+'*30 + 'error' + '+'*30)
print(error)
print('+'*30 + 'error' + '+'*30)
middleware.py文件
这里修改请求过程，目的为了获取ajax加载的url
from selenium import webdriver
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from scrapy.http.response.html import HtmlResponse
# 用selenium重写请求过程，实现去爬取一些用ajax加载的页面
# 一些点赞数，评论数，喜欢数，推荐阅读的文章链接都是ajax加载的。
class SeleniumDownloadMiddleware(object):
def __init__(self):
self.browser = webdriver.Chrome() #
self.wait = WebDriverWait(self.browser,10)
def process_request(self,request,spider):
self.browser.get(request.url)
print('我正在用selenium自动化工具下载url')
time.sleep(1)
try:
while True:
# 这里因为有些文章下方有许多加载更多，在文章被一下专栏收录里，所以要重复点击
showmore = self.browser.find_element_by_class_name('show-more')
showmore.click()
time.sleep(0.3)
if not showmore:
break
except:
pass
source = self.browser.page_source
response = HtmlResponse(url=self.browser.current_url,request=request,body=source,encoding='utf-8')
return response