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.
89 lines
4.1 KiB
89 lines
4.1 KiB
import scrapy
|
|
from uuid import uuid4
|
|
import re
|
|
from demo1.custom_settings_conf import *
|
|
from demo1.items import Shouyelianjie
|
|
from scrapy.utils.project import get_project_settings
|
|
from scrapy.spiders import CrawlSpider, Rule
|
|
from scrapy.linkextractors import LinkExtractor
|
|
import pymysql
|
|
import logging
|
|
import json
|
|
import time
|
|
from lxml import etree
|
|
from urllib import parse
|
|
from demo1.Util import Util_WANG
|
|
#山西省工业和信息厅
|
|
class sxsshangwutingSpider(scrapy.Spider,Util_WANG):
|
|
name = 'sxgongxintingSpider'
|
|
settings = get_project_settings()
|
|
allowed_domains = ['gxt.shanxi.gov.cn']
|
|
custom_settings = custom_settings_conf_sxgongxintingSpider
|
|
start_urls = ['http://gxt.shanxi.gov.cn/web/cateList.html?id=26&word=&pageIndex=1']
|
|
|
|
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="zwgk-ul"]/li[not(@style)]')
|
|
for li in lis:
|
|
item=Shouyelianjie()
|
|
item['laiyuan']='山西省工业和信息厅'
|
|
item['lianjie']=response.urljoin( li.xpath('./a/@href').extract_first())
|
|
shijian=li.xpath('./i/text()').extract_first()
|
|
item['shijian']=datetime.datetime.strptime(shijian,'%Y-%m-%d %H:%M:%S').strftime('%Y-%m-%d')
|
|
item['biaoti']=li.xpath('./a/text()').extract_first()
|
|
#测试用得
|
|
#item['lianjie']='http://gxt.shanxi.gov.cn/web/content.html?id=1511'
|
|
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:
|
|
if Util_WANG.pos_url(item, self.settings):
|
|
yield item
|
|
else:
|
|
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:
|
|
if Util_WANG.pos_url(item, self.settings):
|
|
yield item
|
|
else:
|
|
yield scrapy.Request(url=item['lianjie'], meta={'item': item}, callback=self.page_url)
|
|
if self.settings.get("ISQUANPA"):
|
|
try:
|
|
next_page=response.urljoin(response.xpath('//a[contains(text(),"下一页")]/@href').extract_first())
|
|
# if curry_page < count_page:
|
|
# urls = 'https://www.mct.gov.cn/whzx/ggtz/index_' + str(curry_page) + '.htm'
|
|
# yield scrapy.Request(url=urls, callback=self.parse)
|
|
current_url=response.url
|
|
if next_page!=current_url:
|
|
yield scrapy.Request(url=next_page, 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')
|
|
def page_url(self,response):
|
|
item=response.meta['item']
|
|
item['xiangqing']=response.xpath('//*[contains(@class,"textbody")]').extract_first()
|
|
wenjiande=response.xpath('//*[@class="attachment"]').extract_first()
|
|
if wenjiande is not None:
|
|
item['xiangqing']+=wenjiande
|
|
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
|