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.
83 lines
3.6 KiB
83 lines
3.6 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 fagaiweiSpider(scrapy.Spider,Util_WANG):
|
|
name='fagaiweiSpider'
|
|
settings = get_project_settings()
|
|
allowed_domains = ['ndrc.gov.cn']
|
|
custom_settings = custom_settings_conf_fagaiwei
|
|
start_urls=['https://www.ndrc.gov.cn/xxgk/zcfb/tz/index.html']
|
|
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 parse(self, response):
|
|
lis=response.xpath('//*[@class="list"]/ul/li[not(@class="empty")]')
|
|
for lis_sigl in lis:
|
|
item=Shouyelianjie()
|
|
item['biaoti']=lis_sigl.xpath('./a/@title').extract_first()
|
|
item['shijian']=lis_sigl.xpath('.//span/text()').extract_first().replace('/','-')
|
|
item['lianjie']='https://www.ndrc.gov.cn/xxgk/zcfb/tz'+lis_sigl.xpath('.//a/@href').extract_first().strip('.')
|
|
item['laiyuan']='发改委'
|
|
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 = response.xpath('//*[@class="page"]//script').re('\d{1,2}.*?,.*?\d{1,2}')[0].split(',')
|
|
count_page = int(next_page[0].strip())
|
|
curry_page = int(next_page[-1].strip())+1
|
|
if curry_page < count_page:
|
|
urls = 'https://www.ndrc.gov.cn/xxgk/zcfb/tz/index_' + str(curry_page) + '.html'
|
|
yield scrapy.Request(url=urls, callback=self.parse)
|
|
except Exception as e:
|
|
logging(e)
|
|
logging.info('因为异常：全部爬取完毕')
|
|
else:
|
|
logging.info('全部爬取完毕')
|
|
|
|
|
|
# 测试页面的直接
|
|
# urls='https://www.ndrc.gov.cn/xxgk/zcfb/tz/202004/t20200414_1225669.html'
|
|
# yield scrapy.Request(url=urls,callback=self.page_url,meta={'item':Shouyelianjie()})
|
|
|
|
def page_url(self,response):
|
|
item=response.meta['item']
|
|
txts=response.xpath('//*[@class="article_l"]/*[not(contains(@class,"shezhi"))]')
|
|
a=''
|
|
for txt in txts:
|
|
a+=txt.extract()
|
|
item['xiangqing']=a
|
|
self.tihuan_a_return(item, self.settings.get('FILE_PATH'),response)
|
|
self.tihuan_img_return(item, self.settings.get('MESSAGE'),response)
|
|
yield item
|
|
def a_fun(self,href):
|
|
pass
|
|
def img_fun(self, src):
|
|
pass
|