You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
73 lines
3.4 KiB
73 lines
3.4 KiB
import scrapy
|
|
from uuid import uuid4
|
|
import re
|
|
from scrapy.spiders import CrawlSpider
|
|
from demo1.custom_settings_conf import *
|
|
from demo1.items import Shouyelianjie
|
|
from scrapy.utils.project import get_project_settings
|
|
import pymysql
|
|
import logging
|
|
import json
|
|
import time
|
|
from lxml import etree
|
|
from urllib import parse
|
|
from demo1.Util import Util_WANG
|
|
class ziranweiyuanhuiSpider(scrapy.Spider,Util_WANG):
|
|
name = 'ziranweiyuanhuiSpider'
|
|
settings = get_project_settings()
|
|
allowed_domains = ['nsfc.gov.cn']
|
|
custom_settings = custom_settings_conf_ziranweiyuanhui
|
|
def __init__(self, name=None, **kwargs):
|
|
self.db = pymysql.connect(
|
|
host=self.settings['MYSQL_HOST'],
|
|
database=self.settings['MYSQL_DATABASE'],
|
|
user=self.settings['MYSQL_USER'],
|
|
password=self.settings['MYSQL_PASSWORD'],
|
|
port=3306,
|
|
charset='utf8',
|
|
cursorclass=pymysql.cursors.DictCursor,
|
|
use_unicode=True
|
|
)
|
|
self.cursor = self.db.cursor()
|
|
def start_requests(self):
|
|
yield scrapy.Request(url=self.return_start_url(),callback=self.parse)
|
|
|
|
#ceshixianye
|
|
#yield scrapy.Request(url='http://www.nsfc.gov.cn/publish/portal0/tab442/info76617.htm',callback=self.page_url,meta={'item':Shouyelianjie()})
|
|
def return_start_url(self,page=1):
|
|
return 'http://www.nsfc.gov.cn/publish/portal0/tab442/module1178/page'+str(page)+'.htm'
|
|
def parse(self, response):
|
|
news=response.xpath('//*[@class="clearfix"]')
|
|
for news_list in news:
|
|
item=Shouyelianjie()
|
|
item['lianjie']='http://www.nsfc.gov.cn'+news_list.xpath('.//*[@class="fl"]/a/@href').extract_first()
|
|
item['laiyuan']='国家自然科学基金委员会'
|
|
item['shijian']=news_list.xpath('.//*[@class="fr"]/text()').extract_first()
|
|
item['biaoti']=news_list.xpath('.//a/text()').extract_first()
|
|
if not self.settings.get("ISQUANPA"):
|
|
self.cursor.execute(
|
|
'select count(title_url) as nums FROM t_policy where title_url ="{}"'.format(item['lianjie']))
|
|
res = self.cursor.fetchall()[0].get('nums')
|
|
if res == 0:
|
|
yield scrapy.Request(url=item['lianjie'],meta={'item':item},callback=self.page_url)
|
|
else:
|
|
logging.info('这个链接已经爬过了-----：' + item['lianjie'])
|
|
else:
|
|
yield scrapy.Request(url=item['lianjie'], meta={'item': item}, callback=self.page_url)
|
|
if self.settings.get("ISQUANPA"):
|
|
try:
|
|
next_page='http://www.nsfc.gov.cn'+response.xpath('//a[@class="Normal"]')[-2].xpath('@href').extract_first()
|
|
yield scrapy.Request(url=next_page,callback=self.parse)
|
|
except:
|
|
logging.info('全部爬取完毕')
|
|
def page_url(self,response):
|
|
item=response.meta['item']
|
|
txt=response.xpath('//*[@class="content_xilan"]').extract_first()
|
|
item['xiangqing']=txt.replace('\u3000','')
|
|
self.tihuan_a_return(item,self.settings.get('FILE_PATH'))
|
|
self.tihuan_img_return(item,self.settings.get('MESSAGE'))
|
|
yield item
|
|
def a_fun(self,href):
|
|
return 'http://www.nsfc.gov.cn'+href
|
|
def img_fun(self, src):
|
|
return 'http://www.nsfc.gov.cn'+src
|