89 lines
3.0 KiB
Python
89 lines
3.0 KiB
Python
import scrapy
|
|
from scrapy import Request
|
|
|
|
from commons.constants.mysteel import PageType
|
|
|
|
|
|
class SteelSectionSpider(scrapy.Spider):
|
|
name = "steel_section"
|
|
start_urls = [
|
|
(PageType.SECTION_LIST, "https://list1.mysteel.com/market/p-227-----010107-0-01010502-------1.html"),
|
|
]
|
|
cookie = None
|
|
user_agent = None
|
|
|
|
def start_requests(self):
|
|
for source, url in self.start_urls:
|
|
yield Request(
|
|
method='GET',
|
|
url=url,
|
|
headers={
|
|
'User-Agent': self.user_agent,
|
|
},
|
|
meta={'source': source, 'type': source}
|
|
)
|
|
|
|
def parse(self, response, **kwargs):
|
|
if response.meta['type'] == PageType.SECTION_LIST:
|
|
yield from self.parse_section_list(response)
|
|
if response.meta['type'] == PageType.SECTION_DETAIL:
|
|
yield from self.parse_section_detail(response)
|
|
|
|
def parse_section_list(self, response):
|
|
for item in response.xpath('//*[@id="articleList"]/ul/li/a'):
|
|
uri = item.xpath('@href').get()
|
|
name = item.xpath('text()').get()
|
|
print(uri, name)
|
|
if '福州市场工角槽钢价格行情' not in name:
|
|
continue
|
|
yield Request(
|
|
method='GET',
|
|
url=uri,
|
|
headers={
|
|
'User-Agent': self.user_agent,
|
|
},
|
|
cookies=self.cookie,
|
|
meta={'source': name, 'type': PageType.SECTION_DETAIL}
|
|
)
|
|
|
|
def parse_section_detail(self, response):
|
|
title = response.xpath('//*[@id="content-title"]/text()').get()
|
|
date = title.split('日')[0].replace('年', '-').replace('月', '-')
|
|
|
|
for item in response.xpath('//*[@id="marketTable"]/tr[position()>2]'):
|
|
line = [cell.xpath('text()').get().strip() for cell in item.xpath('td')]
|
|
print(line)
|
|
if len(line) < 7:
|
|
continue
|
|
name, spec, material, source, price, fluctuating, *_ = line
|
|
yield {
|
|
'name': name,
|
|
'spec': spec,
|
|
'material': material,
|
|
'source': source,
|
|
'price': int(price),
|
|
'fluctuating': 0 if fluctuating == '-' else int(fluctuating),
|
|
'date': date
|
|
}
|
|
|
|
|
|
if __name__ == '__main__':
|
|
import json
|
|
|
|
from spiders import run_spider, MysteelCookieTools
|
|
from commons.models.steel_section import SteelSection
|
|
from core.factory import ClientApp
|
|
|
|
# cookie 读取
|
|
cookie = MysteelCookieTools.get_cookies()
|
|
# 爬取
|
|
SteelSectionSpider.cookie = cookie
|
|
SteelSectionSpider.user_agent = MysteelCookieTools.user_agent
|
|
file_path = run_spider(SteelSectionSpider)
|
|
# 入库
|
|
data = json.loads(open(file_path, 'r', encoding='utf-8').read())
|
|
with ClientApp().app_context():
|
|
for item in data:
|
|
print(item)
|
|
SteelSection(**item).upsert()
|