第一次增加

main.py

@@ -0,0 +1,28 @@
+import bigSortSpider
+import spider
+
+
+
+
+class Main:
+    def __init__(self):
+        self.spider = spider.Spider()
+
+    def main(self):
+        url = 'http://www.zhongyoo.com/name/'
+        big_hrefs = self.spider.big_sort_spider(url)
+        for href in big_hrefs:
+            more_hrefs = self.spider.small_sort_spider(href)
+
+            if more_hrefs != []:
+                for more_href in more_hrefs:
+                    detail,sort = self.spider.more_medicinal_detail_href(more_href)
+                    print(sort)
+                    print(detail)
+            else:
+                detail,sort = self.spider.medicinal_detail_href(href)
+                print(sort)
+                print(detail)
+
+if __name__ == '__main__':
+    mian = Main().main()

spider.py

@@ -0,0 +1,57 @@
+import time
+
+from selenium import webdriver
+from lxml import etree
+
+
+
+class Spider:
+    def __init__(self):
+        self.bro = webdriver.Chrome()
+
+
+    def small_sort_spider(self,url):
+        def link_get(resp, xpath):
+            html = etree.HTML(resp)
+            link = html.xpath(xpath)
+            return link
+
+        self.bro.get(url)
+        resp = self.bro.page_source
+        time.sleep(1)
+        more_href = link_get(resp,"/html/body/div[5]/div[2]/div[3]/div/dl/dd/ul/li[@class='more']/a/@href")
+        return more_href
+
+    def big_sort_spider(self, url):
+        def link_get(resp,xpath):
+            html = etree.HTML(resp)
+            link = html.xpath(xpath)
+            return link
+        self.bro.get(url)
+        resp = self.bro.page_source
+        href = link_get(resp,'/html/body/div[5]/div/div[1]/div/a/@href')
+        return href
+
+    def more_medicinal_detail_href(self,url):
+        def link_get(resp,xpath):
+            html = etree.HTML(resp)
+            link = html.xpath(xpath)
+            return link
+        self.bro.get(url)
+        resp = self.bro.page_source
+        detail = link_get(resp,'/html/body/div[5]/div[2]/div[4]/div/dl/dd/ul/li/a/@href')
+        sort = link_get(resp,'/html/body/div[5]/div[2]/div[1]/div[1]/b/h1/text()')
+
+        return detail,sort
+
+    def medicinal_detail_href(self,url):
+        def link_get(resp,xpath):
+            html = etree.HTML(resp)
+            link = html.xpath(xpath)
+            return link
+        self.bro.get(url)
+        resp = self.bro.page_source
+        detail = link_get(resp,'/html/body/div[5]/div[2]/div[4]/div/dl/dd/ul/li/a/@href')
+        sort = link_get(resp,"/html/body/div[5]/div[2]/div[1]/div[1]/b/h1/text()")
+
+        return detail,sort