add feature: use date range in boundary option #50

README-CN.md

@@ -59,7 +59,7 @@ optional arguments:
 - `-r retry` 最大重试次数（默认值：`2`）
 - `-i interval` 请求间隔（默认值：`1`，单位：秒）
 - `-c cookie` 登录凭据 (需要 cookie 中的 `SUB` 值)
-- `-b boundary` 微博 mid 或 bid 范围（格式：`id:id` 两者之间，`:id` 之前，`id:` 之后，`id` 指定，`:` 全部）
+- `-b boundary` 微博 mid/bid 或日期范围（格式：`id:id` 两者之间，`:id` 之前，`id:` 之后，`id` 指定，`:` 全部）
 - `-n name` 命名模板 (标识符: `url`、`index`、`type`、`mid`、`bid`、`date`、`text`、`name`，类似 ["f-Strings"](https://www.python.org/dev/peps/pep-0498/#abstract) 语法)
 - `-v` 同时下载秒拍视频
 - `-o` 重新下载已保存的文件（默认跳过）

README.md

@@ -62,7 +62,7 @@ Optional arguments
 - `-r retry` max retries (default value: `2`)
 - `-i interval` request interval (default value: `1`, unit: second)
 - `-c cookie` login credential (only need the value of a certain key named `SUB`)
-- `-b boundary` mid/bid range of weibos (format: `id:id` between, `:id` before, `id:` after, `id` certain, `:` all)
+- `-b boundary` mid/bid/date range of weibos (format: `id:id` between, `:id` before, `id:` after, `id` certain, `:` all)
 - `-n name` naming template (identifier: `url`, `index`, `type`, `mid`, `bid`, `date`, `text`, `name`, like ["f-Strings"](https://www.python.org/dev/peps/pep-0498/#abstract) syntax)
 - `-v` download miaopai videos at the same time
 - `-o` overwrite existing files (skipping if exists for default)

weiboPicDownloader.py

@@ -197,6 +197,17 @@ def parse_date(text):
     elif re.search(r'^[\d|-]+$', text):
         return datetime.datetime.strptime(((str(now.year) + '-') if not re.search(r'^\d{4}', text) else '') + text, '%Y-%m-%d').date()
 
+def compare(standard, operation, candidate):
+    for target in candidate:
+        try:
+            result = '>=<'
+            if standard > target: result = '>'
+            elif standard == target: result = '='
+            else: result = '<'
+            return result in operation
+        except TypeError:
+            pass
+
 def get_resources(uid, video, interval, limit):
     page = 1
     size = 25
@@ -227,10 +238,11 @@ def get_resources(uid, video, interval, limit):
                     mblog = card['mblog']
                     if 'isTop' in mblog and mblog['isTop']: continue
                     mid = int(mblog['mid'])
-                    mark = {'mid': mid, 'bid': mblog['bid'], 'date': parse_date(mblog['created_at']), 'text': mblog['text']}
+                    date = parse_date(mblog['created_at'])
+                    mark = {'mid': mid, 'bid': mblog['bid'], 'date': date, 'text': mblog['text']}
                     amount += 1
-                    if mid < limit[0]: exceed = True
-                    if mid < limit[0] or mid > limit[1]: continue
+                    if compare(limit[0], '>', [mid, date]): exceed = True
+                    if compare(limit[0], '>', [mid, date]) or compare(limit[1], '<', [mid, date]): continue
                     if 'pics' in mblog:
                         for index, pic in enumerate(mblog['pics'], 1):
                             if 'large' in pic:
@@ -312,10 +324,12 @@ def download(url, path, overwrite):
 boundary = args.boundary.split(':')
 boundary = boundary * 2 if len(boundary) == 1 else boundary
 numberify = lambda x: int(x) if re.search(r'^\d+$', x) else bid_to_mid(x)
+dateify = lambda t: datetime.datetime.strptime(t, '@%Y%m%d').date()
+parse_point = lambda p: dateify(p) if p.startswith('@') else numberify(p)
 try:
-    boundary[0] = 0 if boundary[0] == '' else numberify(boundary[0])
-    boundary[1] = float('inf') if boundary[1] == '' else numberify(boundary[1])
-    assert boundary[0] <= boundary[1]
+    boundary[0] = 0 if boundary[0] == '' else parse_point(boundary[0])
+    boundary[1] = float('inf') if boundary[1] == '' else parse_point(boundary[1])
+    if type(boundary[0]) == type(boundary[1]): assert boundary[0] <= boundary[1]
 except:
     quit('invalid id range {}'.format(args.boundary))