sun
import scrapy
from sun0769.items import Sun0769Item
import time
class SunSpider(scrapy.Spider):
name = 'sun'
allowed_domains = ['wz.sun0769.com']
start_urls = ['https://wz.sun0769.com/political/index/search?keyword=%E6%8A%95%E8%AF%89&page=1']
def parse(self, response):
####停顿1s
time.sleep(2)
html_list = response.xpath("//ul[@class='title-state-ul']/li")
# print(html_list..extract())
# test_list = html_list.xpath("./li/span[1]/text()")
# print(test_list.extract())
for list_ul in html_list:
item= {}
item["number"]=list_ul.xpath("./span[1]/text()").extract_first()
item["status"]=list_ul.xpath("normalize-space(./span[2])").extract_first()
item["title"]=list_ul.xpath("normalize-space(./span[3]/a)").extract_first()
item["time_1"]=list_ul.xpath("normalize-space(./span[4])").extract_first()
item["time_2"]=list_ul.xpath("normalize-space(./span[5])").extract_first()
item["url"]=list_ul.xpath("normalize-space(./span[3]/a/@href)").extract_first()
item["url"]="https://wz.sun0769.com/"+ item["url"]
# print(item)
# print(next_url)
yield scrapy.Request(url=item["url"],callback=self.parse_detail,meta={"item":item})
##获取详情页url返回给scrapy处理----parse_detail
###parse_detail不能有（）否则就是调用
####把item=Sun0769Item()内容，返回给parse_detail处理添加详情页内容
#####翻页
next_url = response.xpath("//a[@class='arrow-page prov_rota']/@href").extract_first()
next_url = "https://wz.sun0769.com" + next_url
# print(next_url)
######next_url 不等于None
if next_url is not None:
#######url新链接返回给parse(self, response): 处理
yield scrapy.Request(url=next_url,callback=self.parse)
def parse_detail(self,response):###处理详情页
item = response.meta["item"]
###获取详情页留意
item["content"]=response.xpath("normalize-space(//div[@class='details-box']/pre)").extract_first()
item["img_url"]=response.xpath("//div[@class='clear details-img-list Picture-img']/img/@src").extract_first()
# print(item)
print(item["img_url"])
yield item
pipl
# 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 pymysql
import sun0769.settings
from sun0769.settings import SQL_HOST,SQL_USER,SQL_PASSWD
# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
####定义mysqlPipeline ###setting
class mysqlPipeline(object):
##链接数据库
##open_spider(self, spider): 爬虫开启时候执行一次
def open_spider(self, spider):
self.conn = pymysql.connect(host=,user=SQL_USER,passwd=SQL_PASSWD,db='scrapy',charset='utf8mb4',cursorclass=pymysql.cursors.DictCursor) #连接数据库
def process_item(self, item, spider):
#添加数据到chengjiao表中
self.conn.query(
"insert sun0769(number,status,title,time_1,time_2,url,content,img_url)" #需要插入的字段
"values('{}','{}','{}','{}','{}','{}','{}','{}')".format(
item['number'],item['status'],item['title'],item['time_1'],item['time_2'],item['url'],item['content'],str(item['img_url']) #爬取项目中定义的字段
))
self.conn.commit()#执行添加
##close_spider(self, spider): 爬虫关闭时候执行一次
def close_spider(self, spider):
self.conn.close() #关闭连接
yield item
class Sun0769Pipeline:
def process_item(self, item, spider):
# sun0769.settings.SQL_HOST
# spider.settings.get("SQL_USER")
return item
midd
# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
class Sun0769SpiderMiddleware:
# 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, 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 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)
class Sun0769DownloaderMiddleware:
# 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
def process_request(self, request, spider):
# Called for each request that goes through the downloader
# middleware.
# Must either:
# - return None: continue processing this request
# - or return a Response object
# - or return a Request object
# - or raise IgnoreRequest: process_exception() methods of
# installed downloader middleware will be called
return None
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)
###### ##随机UA头########
from fake_useragent import UserAgent
class RandomUserAgentMiddleware(object):
def process_request(self, request, spider):
ua = UserAgent()
request.headers['User-Agent'] = ua.random
items
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html
import scrapy
class Sun0769Item(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
number = scrapy.Field()
status = scrapy.Field()
title = scrapy.Field()
time_1 = scrapy.Field()
time_2 = scrapy.Field()
url = scrapy.Field()
content = scrapy.Field()
img_url = scrapy.Field()
sett
# Scrapy settings for sun0769 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
###项目名字
BOT_NAME = 'sun0769'
####爬虫位置
SPIDER_MODULES = ['sun0769.spiders']
##新建爬虫位置
NEWSPIDER_MODULE = 'sun0769.spiders'
SQL_HOST = '****'
SQL_USER = 'scrapy'
SQL_PASSWD = 'scrapy'
###设置输出日志等级
LOG_LEVEL = 'WARNING'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# from fake_useragent import UserAgent ##随机UA头
# USER_AGENT = UserAgent(verify_ssl=False).random
# Obey robots.txt rules
####默认情况下遵守rebots协议 False
ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
####最大并发请求数量
#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
##下载延迟，每次请求前等待3秒
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
####每个域名最大并发数
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
###每个IP最大并发数
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
####cookies是否开启默认开启
#COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
# 默认请求头
#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
###爬虫中间件
#SPIDER_MIDDLEWARES = {
# 'sun0769.middlewares.Sun0769SpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
###下载中间件
DOWNLOADER_MIDDLEWARES = {
'sun0769.middlewares.RandomUserAgentMiddleware': 300,
'sun0769.middlewares.Sun0769DownloaderMiddleware': 543,
}
# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
# 插件
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
#########items 权重
ITEM_PIPELINES = {
'sun0769.pipelines.mysqlPipeline': 299,
'sun0769.pipelines.Sun0769Pipeline': 298,
}
##自动限速 默认关闭
# 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
#####HTTP缓存默认关闭
# 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'
