MOD: 引入 flake8 和 pylint 检查，让代码看起来更 Pythonic

.pylintrc

@@ -0,0 +1,8 @@
+[MASTER]
+
+[MESSAGE CONTROL]
+disable=missing-docstring,
+        invalid-name
+
+[FORMAT]
+max-line-length=100

Pipfile

@@ -6,6 +6,8 @@ name = "pypi"
 [dev-packages]
 pylint = "*"
 ipython = "*"
+flake8 = "*"
+"autopep8" = "*"
 
 [packages]
 requests = "*"

crawl/album.py

@@ -52,10 +52,10 @@ def get_album_summary(album_id, uid=crawler.uid):
     photo_list = layer['list']
     photo_count = len(photo_list)
     for idx, p in enumerate(photo_list):
-        id = int(p['id'])
+        pid = int(p['id'])
         date_str = p['date'] if config.py3 else p['date'].encode('utf8')
         photo = {
-            'id': id,
+            'id': pid,
             'uid': uid,
             'album_id': album_id,
             'pos': idx,
@@ -66,17 +66,17 @@ def get_album_summary(album_id, uid=crawler.uid):
             'src': get_image(p['large']),
             'comment': p['commentCount'],
             'share': p['shareCount'],
-            'like': get_likes(id, 'photo'),
+            'like': get_likes(pid, 'photo'),
             'view': p['viewCount']
         }
         Photo.insert(**photo).on_conflict('replace').execute()
         if photo['comment']:
-            get_comments(id, 'photo', owner=uid)
+            get_comments(pid, 'photo', owner=uid)
         if photo['comment'] or photo['share']:
-            get_comments(id, 'photo', global_comment=True, owner=uid)
+            get_comments(pid, 'photo', global_comment=True, owner=uid)
 
-        print(u'      photo {id}: {title}, {comment}/{share}/{like}/{view}'.format(
-            id=id,
+        print(u'      photo {pid}: {title}, {comment}/{share}/{like}/{view}'.format(
+            pid=pid,
             title=p['title'][:24],
             comment=photo['comment'],
             share=photo['share'],
@@ -90,20 +90,20 @@ def get_album_summary(album_id, uid=crawler.uid):
 def get_album_list_page(page, uid=crawler.uid):
     param = {
         'offset': page*config.ITEMS_PER_PAGE,
-        'limit': config.ITEMS_PER_PAGE 
+        'limit': config.ITEMS_PER_PAGE
     }
     resp = crawler.get_url(config.ALBUM_LIST_URL.format(uid=uid), param)
     albums = json.loads(re.findall(r"'albumList': (\[.*\]),", resp.text)[0])
 
     for a in albums:
-        id = int(a['albumId'])
-        print(u'    album {id}: {name}, has {count} photos'.format(
-            id=id,
+        aid = int(a['albumId'])
+        print(u'    album {aid}: {name}, has {count} photos'.format(
+            aid=aid,
             name=a['albumName'],
             count=a['photoCount']
         ))
         if a["photoCount"]:
-            get_album_summary(id, uid)
+            get_album_summary(aid, uid)
 
     count = len(albums)
     print('  get {count} albums on list page {page}'.format(count=count, page=page))

crawl/blog.py

@@ -1,7 +1,6 @@
 # coding: utf8
 
 from datetime import datetime
-import json
 
 from config import config
 from models import Blog
@@ -25,9 +24,9 @@ def load_blog_list(page, uid=crawler.uid):
     r = crawler.get_json(config.BLOG_LIST_URL.format(uid=uid), {'curpage': page})
 
     for b in r['data']:
-        id = int(b['id'])
+        bid = int(b['id'])
         blog = {
-            'id': id,
+            'id': bid,
             'uid': uid,
             't': datetime.strptime(b['createTime'], "%y-%m-%d %H:%M:%S"),
             'category': b['category'],
@@ -39,27 +38,27 @@ def load_blog_list(page, uid=crawler.uid):
             'read': b['readCount']
         }
 
-        blog['content'] = load_blog_content(id, uid)
+        blog['content'] = load_blog_content(bid, uid)
 
         Blog.insert(**blog).on_conflict('replace').execute()
 
         total_comment = 0
         if blog['comment']:
-            get_comments(id, 'blog', owner=uid)
+            get_comments(bid, 'blog', owner=uid)
         if blog['comment'] or blog['share']:
-            total_comment = get_comments(id, 'blog', global_comment=True, owner=uid)
+            total_comment = get_comments(bid, 'blog', global_comment=True, owner=uid)
         if blog['like']:
-            get_likes(id, 'blog')
+            get_likes(bid, 'blog')
 
-        print(u'  crawled blog {id} {title} with {comment}/{share}/{like}/{read}, and {total_comment}'.format(
-            id=id,
+        print(u'  crawled blog {bid} {title} with {comment}/{share}/{like}/{read}'.format(
+            bid=bid,
             title=blog['title'],
             comment=blog['comment'],
             share=blog['share'],
             like=blog['like'],
-            read=blog['read'],
-            total_comment=total_comment
+            read=blog['read']
         ))
+        print(u'        and total comments {total_comment}'.format(total_comment=total_comment))
 
     return r['count']