Fix celebrity thumb

Signed-off-by: Ein Verne <einverne@gmail.com>
einverne · Jul 21, 2018 · 0d0ec12 · 0d0ec12
1 parent 9a69fad
commit 0d0ec12
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -1,6 +1,8 @@
 douban downloader
 =======================
 
+一个简单的下载豆瓣相册、图集、影人图片的小脚本
+
 A simple python script to download douban albums and celebrity
 
 
@@ -23,6 +25,10 @@ Introduction
         douban-dl https://www.douban.com/people/einverne/
 
 
+4. 电影剧照
+
+        douban-dl https://movie.douban.com/subject/26804147
+
 Installation
 ------------
 
@@ -42,6 +48,8 @@ Usage
 
 `path` is the folder where images saved, defaults to `./douban`.
 
+如果没有指定 `path` ，默认会保存到当前目录下 douban 文件夹中。
+
 License
 -------
 

diff --git a/douban/celebrity.py b/douban/celebrity.py
@@ -21,17 +21,28 @@ def photos(self):
                 # https://img3.doubanio.com/view/photo/thumb/public/p2156276775.jpg
                 # https://img3.doubanio.com/view/photo/raw/public/p2156276775.jpg
                 # https://img3.doubanio.com/view/photo/photo/public/p2156276775.webp
-                yield photo.a['href'], photo.img['src'].replace("photo/thumb", "photo/raw")
+                # src https://img3.doubanio.com/view/photo/m/public/p2179264053.webp
+                src = photo.img['src']
+                if 'm/public' in src:
+                    src = src.replace("photo/m", "photo/raw")
+                if 'photo/thumb' in src:
+                    src = src.replace("photo/thumb", "photo/raw")
+                if 'webp' in src:
+                    src = src.replace("webp", "jpg")
+                yield photo.a['href'], src
             start += step
 
     def __photos(self, start):
         params = {
             "type": "C",
             "start": start,
-            "sortby": "vote",
+            "sortby": "like",
             "size": "a",
             "subtype": "a"
         }
-        r = requests.get(self.url, params=params)
+        header = {
+            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36'
+        }
+        r = requests.get(self.url, params=params, headers=header)
         soup = BeautifulSoup(r.text, "html.parser")
         return soup.find_all("div", class_="cover")