煎蛋网妹子图

Author: ZKeeer

JandanSpider/Util/Downloader.py

@@ -11,7 +11,7 @@
 second_level = "./DownLoad/Image/"
 
 
-def page_downloader(tar_url, host=None):
+def page_downloader(tar_url, Referer=None, host=None):
     url_content = ""
     try:
         url_content = requests.get(tar_url,

JandanSpider/demo.py

@@ -6,7 +6,7 @@
 page_list = []
 max_page = 0
 RegEx_img = "<a href=\"([\w\/\.]+?)\" target"
-RegEx_max_page = "\"current-comment-page\">[(\d*?)]</span>"
+RegEx_max_page = "\"current-comment-page\">\[(\d*?)\]</span>"
 
 #获取访问过的页面列表
 rec_dict = Record.Read()
@@ -15,10 +15,9 @@
 #获取最新的页面值
 content = Downloader.page_downloader("http://jandan.net/ooxx")
 max_page = PageParser.parser(content, RegEx=RegEx_max_page)[0]
-print("解析结果：{}".format(PageParser.parser(content, RegEx=RegEx_max_page)))
 
 #构造页面地址
-for index in range(max_page, 0, -1):
+for index in range(int(max_page), 0, -1):
     page_list.append("http://jandan.net/ooxx/page-{}#comments".format(index))
 
 #遍历页面
@@ -43,5 +42,5 @@
     for t in threads_list:
         t.join()
 
-#把最新的页面，最新的页数，访问过的页面记录
-Record.Write({"page_num": index, "page_url": page_item, "viewed": page_viewed})
+# 把最新的页面，最新的页数，访问过的页面记录
+Record.Write({"page_num": int(max_page), "page_url": page_list[0], "viewed": page_viewed})