历史价格

downloader.py

@@ -38,12 +38,6 @@ def getsource(url):
     return response
 
 def useRequests(url):
-
-    def write2html(res):
-        filename = 'historyPrice.html'
-        with open(filename, mode = 'w+', encoding='utf-8') as fd:
-            fd.write(res)
-
     try:
         session = requests.Session()
         res = session.get(url, headers = headers)
@@ -52,7 +46,6 @@ def useRequests(url):
         res.encoding = res.apparent_encoding
         res = etree.HTML(res.text)
         source = etree.tostring(res, encoding = 'utf-8', pretty_print = True, method = 'html').decode('utf-8')
-        # write2html(res)
         return source
     except BaseException as e:
         print(e)
@@ -61,7 +54,7 @@ def useRequests(url):
 
 
 if __name__ == "__main__":
-    jdurl = r"https://item.jd.com/10036840192083.html"
+    jdurl = r"https://item.jd.com/10023043997421.html"
     url = r"https://www.vveby.com/search?keyword=" + jdurl
     print(url)
     useRequests(url)

historyPrice.py

@@ -4,13 +4,36 @@ from lxml import etree
 import settings
 import downloader
 
+def myreplace(text):
+    return text.strip().replace(' ', '').replace("\r\n", '')
+
 class historyPriceItem:
     def __init__(self, id):
-        self.url = 
+        self.url = settings.HISTORY_PRICE_URL + str(id)
+        # self.response = downloader.useRequests(self.url)
+        self.response = etree.parse('historyPrice.html', etree.HTMLParser(encoding = 'utf-8'))
+
+    def gethistoryPrice(self) -> list:
+        
+        reg = r"//div[@class='container']"
+        item = self.response.xpath(reg)[0]
+        item = etree.tostring(item, encoding = 'utf-8', method = 'html').decode('utf-8')
+
+        def getTag(self) -> str:
+            reg = r"//div[@data-content='商品类别：']/text()"
+            tag = self.response.xpath(reg)[0]
+            tag = etree.HTML(tag)
+            tag = myreplace(tag)
+            return tag[5:]
+
+        def get
 
+# tree = etree.tostring(response.xpath(reg)[0], encoding = 'utf-8', method = 'html').decode('utf-8')
 
 if __name__ == '__main__':
-    pass
+    id = "10036840192083"
+    aitem = historyPriceItem(id)
+    aitem.gethistoryPrice()
 
 
 

settings.py

@@ -2,6 +2,8 @@
 
 import os
 
+from hyperlink import URL
+
 # 修改要生成的文件名，下面的是默认，注意要用.csv结尾
 FILENAME_CSV = {
     "牛奶": "milk.csv",
@@ -40,4 +42,5 @@ USER_AGENT = [
 
 COOKIES_FILENAME = "cookies.json"
 
-# 
+# 历史价格查询网站 vveby.com
+HISTORY_PRICE_URL = r"https://www.vveby.com/search?keyword="