正在进行【作者评论、作者评论个数】等POST表的数据获取。

ysh329 · Aug 16, 2016 · d23edeb · d23edeb
1 parent ace0d11
commit d23edeb
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/spider/crawler.py b/spider/crawler.py
@@ -345,6 +345,7 @@ def getPostDetailInfoDict(self, postUrl):
             commentUserNameTagList = postComment.find_all('a', attrs={"href":postDetailInfoDict['postAuthorUrl'], 'class':''})
             print len(commentUserNameTagList)
             commentUserNameList = commentUserNameTagList#map(lambda tag: tag.a, commentUserNameTagList)
+
             commentContentList = re.findall('<p class="">(.*)</p>', str(postContent))
             userNameAndCommentContentList = map(lambda name, comment: (name, comment), commentUserNameList, commentContentList)