Files
material-api/web/spiders/data_guangdong.py
2024-05-29 10:21:31 +08:00

79 lines
3.0 KiB
Python

import scrapy
from scrapy import Request
class DataGuangdongSpider(scrapy.Spider):
name = "data_guangdong"
start_urls = [
('材料信息价', "http://zjz.gdcd.gov.cn/zjzgdcd/zjxx_clxxj/list.shtml"),
('材料信息价', "http://zjz.gdcd.gov.cn/zjzgdcd/zjxx_clxxj/list_2.shtml"),
('材料信息价', "http://zjz.gdcd.gov.cn/zjzgdcd/zjxx_clxxj/list_3.shtml"),
('材料信息价', "http://zjz.gdcd.gov.cn/zjzgdcd/zjxx_clxxj/list_4.shtml"),
('材料信息价', "http://zjz.gdcd.gov.cn/zjzgdcd/zjxx_clxxj/list_5.shtml"),
]
def start_requests(self):
for source, url in self.start_urls:
yield Request(
method='GET',
url=url,
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
},
meta={'source': source, 'type': 'home'}
)
def parse(self, response, **kwargs):
if response.meta['type'] == 'home':
yield from self.parse_home(response)
elif response.meta['type'] == 'list':
yield from self.parse_list(response)
def parse_home(self, response):
for item in response.xpath('/html/body/div/div[3]/div[2]/div[2]/div/ul/li/a'):
uri = item.xpath('@href').get()
name = item.xpath('text()').get()
if '广东省交通建设工程主要外购材料信息价表' not in name:
continue
yield Request(
method='GET',
url=f'http://zjz.gdcd.gov.cn{uri}',
headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
},
meta={'source': name, 'type': 'list'}
)
def parse_list(self, response):
date = response.xpath('/html/body/div[1]/div[4]/div/div[1]/div[2]/span[2]/text()').get().strip('发布时间:')
source = response.xpath('/html/body/div[1]/div[4]/div/div[1]/div[2]/span[1]/b/text()').get()
for item in response.xpath('//*[@id="zoomcon"]/p/a'):
uri = item.xpath('@href').get()
name = item.xpath('text()').get()
url_prefix = '/'.join(response.url.split('/')[:-1])
print(uri, name)
yield {
'url': f'{url_prefix}/{uri}',
'name': name,
# 'source': response.meta['source'],
'source': source,
'date': date
}
if __name__ == '__main__':
import json
from spiders import run_spider
from commons.models.data_guangdong import DataGuangdong
from core.factory import ClientApp
# 爬取
file_path = run_spider(DataGuangdongSpider)
# 入库
data = json.loads(open(file_path, 'r', encoding='utf-8').read())
with ClientApp().app_context():
for item in data:
print(item)
DataGuangdong(**item).upsert()