rouor
diff --git a/‎爬虫/Include/豆瓣2/analyse.py
Lines changed: 5 additions & 1 deletion b/‎爬虫/Include/豆瓣2/analyse.py
Lines changed: 5 additions & 1 deletion
diff --git a/‎爬虫/Include/豆瓣2/get_comment.py
Lines changed: 5 additions & 2 deletions b/‎爬虫/Include/豆瓣2/get_comment.py
Lines changed: 5 additions & 2 deletions
diff --git a/‎爬虫/Include/豆瓣2/img.jpg
-83 Bytes b/‎爬虫/Include/豆瓣2/img.jpg
-83 Bytes
diff --git a/‎爬虫/Include/豆瓣2/img2.jpg
4.32 KB b/‎爬虫/Include/豆瓣2/img2.jpg
4.32 KB
diff --git a/‎爬虫/Include/豆瓣2/login.py
Lines changed: 1 addition & 0 deletions b/‎爬虫/Include/豆瓣2/login.py
Lines changed: 1 addition & 0 deletions
diff --git a/‎爬虫/Include/豆瓣2/nezha.xls
4 KB b/‎爬虫/Include/豆瓣2/nezha.xls
4 KB
diff --git a/‎爬虫/Include/豆瓣2/score.png
330 Bytes b/‎爬虫/Include/豆瓣2/score.png
330 Bytes
@@ -1,6 +1,7 @@
 import matplotlib.pyplot as plt
 import matplotlib
 import jieba
+import  jieba.analyse
 import xlwt
 import xlrd
 from wordcloud import WordCloud
@@ -88,6 +89,9 @@ def getciyun_most(map):
     plt.axis("off")
 
 def anylaseword(comment):
+    list=['这个','一个','不少','起来','没有','就是','不是','那个','还是','剧情','这样','那样','这种','那种','故事','人物']
+    list.append("这个")
+    print(list)
     commnetstr=''
     c = Counter()
     low=Counter()
@@ -103,7 +107,7 @@ def anylaseword(comment):
                      continue
         commnetstr+=va[3]
     for (k, v) in c.most_common():
-        if v<5:
+        if v<5 or k in list:
             c.pop(k)
             continue
         #print(k,v)
 
@@ -42,10 +42,13 @@ def getcomment(cookies):
     ws = w.add_sheet('sheet1')
     index=1
     while True:
+        header = {
+            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
+        }
         try:
             url = 'https://movie.douban.com/subject/26794435/comments?start='+str(start)+'&limit=20&sort=new_score&status=P&comments_only=1'
             start+=20
-            req = requests.get(url,cookies=cookies)
+            req = requests.get(url,cookies=cookies,headers=header)
             res = req.json()
             res=res['html']
             soup = BeautifulSoup(res, 'lxml')
@@ -72,7 +75,7 @@ def getcomment(cookies):
 
 if __name__ == '__main__':
 
-    cookies=login('15751512041','52cuihuini')
+    cookies=login('15751512041','52cuihuini!')
     getcomment(cookies)
 
 
 
@@ -31,3 +31,4 @@ def login(username,password):
     cookies = requests.utils.dict_from_cookiejar(req.cookies)
     print(cookies)
     return cookies
+login()