init

web/spiders/steel_section.py

@@ -0,0 +1,88 @@
+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()