百家号添加readme

shaojava · Mar 4, 2017 · c511c72 · c511c72
1 parent a41a8a3
commit c511c72
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 0 deletions.
diff --git a/6.爬虫项目源码/11.百家号/baijiahao_cw/README.md b/6.爬虫项目源码/11.百家号/baijiahao_cw/README.md
@@ -0,0 +1,6 @@
+ # 百家号采集
+## BUG
+*  由于使用PhantomJS效率太低
+*  代码风格问题，有些地方的代码太长不符合PEP8
+*  通过get_url.py爬取两天获得50万URL
+*  但是获取id时服务器跑了一星期了才获得4万可用的ID（百家号作者）
diff --git a/6.爬虫项目源码/11.百家号/baijiahao_cw/qucong.py b/6.爬虫项目源码/11.百家号/baijiahao_cw/qucong.py
@@ -0,0 +1,11 @@
+lll = set()
+with open('appid.txt','r') as idfile:
+    for appid in idfile.readlines():
+        lll.add(appid)
+idfile.close()
+print(len(lll))
+with open('sortid.txt','w') as idfile:
+    for appid in lll:
+        idfile.write(appid)
+        idfile.write('\n')
+idfile.close()