细节完善

SpiderWebsite/demo/views.py

@@ -284,7 +284,7 @@ from lxml import etree
 import requests
 
 
-def begin_spider(url, web_name):
+def begin_spider(url, web_name, web=1):
     url = "https://guilin.zbj.com/search/f/?type=new&kw=saas"
     # 设置headers，防止UA验证，Host为要爬取的域名,通过浏览器F12获取User-Agent
     headers = {
@@ -314,10 +314,10 @@ def begin_spider(url, web_name):
 def main():
     begin_spider("https://guilin.zbj.com/search/f/?type=new&kw=saas", "猪八戒")
 
-
+'''
 if __name__ == '__main__':
     main()
-
+'''
 
 
 import json
@@ -358,15 +358,15 @@ def begin_spider(page, url, web_name):
         f.close()
 
 
-def main():
+def main_a():
     for i in range(0, 100, 20):
         begin_spider(i,"https://music.163.com/","网易云")
         time.sleep(1)
 
-
+'''
 if __name__ == '__main__':
     main()
-
+'''
 import re  # 正则表达式进行文字匹配
 from bs4 import BeautifulSoup  # 网页解析获取数据
 import urllib.error,urllib.request
@@ -374,7 +374,7 @@ import xlwt  # 进行excel操作
 
 
 
-def main():
+def main_b():
     baseurl = "https://movie.douban.com/top250?start="
     # 1.爬取网页
     name= '豆瓣top250'
@@ -505,11 +505,11 @@ def saveData(datalist, savepath):
 
 
 
-
+'''
 if __name__ == "__main__":
     main()
     print("爬取完毕！")
-
+'''