fix:

2024-07-09 18:11:22 +08:00
parent e6442b2cf9
commit d2eca25632
7 changed files with 126 additions and 2 deletions
--- a/web/spiders/data_jiangxi.py
+++ b/web/spiders/data_jiangxi.py
@@ -0,0 +1,83 @@
+import scrapy
+from lxml import html, etree
+from scrapy import Request
+
+
+class DataJiangxiSpider(scrapy.Spider):
+    name = "data_jiangxi"
+    start_urls = [
+        ('材料价格', "http://jt.jiangxi.gov.cn/col/col70716/index.html?uid=339408&pageNum=1"),
+        ('材料价格', "http://jt.jiangxi.gov.cn/col/col70716/index.html?uid=339408&pageNum=2"),
+        ('材料价格', "http://jt.jiangxi.gov.cn/col/col70716/index.html?uid=339408&pageNum=3"),
+    ]
+
+    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):
+        rsp = response.xpath('//*[@id="339408"]/script/text()').get()
+        for t in ('<![CDATA[', ']]>', '</record>', '<record>', '</recordset>', '<recordset>', '</datastore>', '<datastore>', '</nextgroup>', '<nextgroup>'):
+            rsp = rsp.replace(t, '')
+        html = etree.HTML(rsp)
+        for item in html.xpath('//li/a'):
+            print(item)
+            uri = item.xpath('@href')[0]
+            name = item.xpath('text()')[0]
+            print(uri, name)
+            if '工程材料价格信息' not in name:
+                continue
+            yield Request(
+                method='GET',
+                url=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('//*[@id="content"]/div[1]/ul/li[3]/span/text()').get().split(' ')[0]
+        source = response.xpath('//*[@id="content"]/div[1]/ul/li[1]/span/text()').get()
+        for item in response.xpath('//*[@id="div_content"]/span/p/a'):
+            uri = item.xpath('@href').get()
+            name = item.xpath('text()').get()
+            print(uri, name)
+            yield {
+                'url': f'http://jt.jiangxi.gov.cn{uri}',
+                'name': name,
+                # 'source': response.meta['source']
+                'source': source,
+                'date': date,
+            }
+
+# todo 江西造价站入库
+
+if __name__ == '__main__':
+    import json
+
+    from spiders import run_spider
+    from commons.models.data_zhejiang import DataZhejiang
+    from core.factory import ClientApp
+
+    # 爬取
+    file_path = run_spider(DataJiangxiSpider)
+    # 入库
+    data = json.loads(open(file_path, 'r', encoding='utf-8').read())
+    with ClientApp().app_context():
+        for item in data:
+            print(item)
+            # DataJiangxi(**item).upsert()