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.
80 lines
3.6 KiB
80 lines
3.6 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
|
|
#山西省中小企业发展促进局
|
|
class cujinjuSpider(scrapy.Spider,Util_WANG):
|
|
name = 'cujinjuSpider'
|
|
settings = get_project_settings()
|
|
allowed_domains = ['xqyj.shanxi.gov.cn']
|
|
custom_settings = custom_settings_conf_cujinjuSpider
|
|
start_urls = ['http://xqyj.shanxi.gov.cn/v2/html/tzgg/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="page_list"]//li')
|
|
for li in lis:
|
|
item=Shouyelianjie()
|
|
item['biaoti']=li.xpath('./a/@title').extract_first()
|
|
item['lianjie']=response.urljoin(li.xpath('./a/@href').extract_first())
|
|
item['laiyuan']='山西省小企业促进局'
|
|
item['shijian']=li.xpath('./sapn/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_item)
|
|
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_item)
|
|
if self.settings.get("ISQUANPA"):
|
|
try:
|
|
next_page=response.xpath('//a[@class="next-page"]/@onclick').re('\'index.*')
|
|
if len(next_page)>0:
|
|
next_page[0]=next_page[0].strip('\'')
|
|
yield scrapy.Request(url='http://xqyj.shanxi.gov.cn/v2/html/tzgg/'+next_page[0],callback=self.parse)
|
|
except:
|
|
logging.info('全部爬取完毕')
|
|
def page_item(self,response):
|
|
item=response.meta['item']
|
|
item['xiangqing']=response.xpath('//*[@class="doc_content"]').extract_first().replace('192.168.143.1','xqyj.shanxi.gov.cn')
|
|
self.tihuan_a_return(item, self.settings.get('FILE_PATH'), response)
|
|
self.tihuan_img_return(item, self.settings.get('MESSAGE'), response)
|
|
# if item.get('wenjian') is not None:
|
|
# for wenjians in item['wenjian'][:]:
|
|
# if '_' in wenjians['file_name']:
|
|
# self.cursor.execute(
|
|
# 'select count(file_url) as nums FROM t_policy_file_crawl where file_url ="{}"'.format(wenjians['file_url']))
|
|
# res = self.cursor.fetchall()[0].get('nums')
|
|
# if res != 0:
|
|
# item['file_name'].remove(wenjians)
|
|
# logging.info(item)
|
|
yield item
|
|
def a_fun(self,href):
|
|
print()
|
|
def img_fun(self, src):
|
|
print()
|