feat: 添加通过文件添加关键词的功能

KEYWORD_LIST既可以是关键词列表如[keyword1, keyword2,keyword3]，也可以是保存这关键词的txt文件路径，如'keyword_list.txt'，每一个要搜索的关键词一行，如果一行中包含多个以空格分隔的关键词，则这些关键词为一个关键词，如内容：
迪丽热巴
尿布 啤酒

表示第一个关键词搜索包含迪丽热巴的微博；第二个表示搜索同时包含尿布和啤酒的微博。

Issue dataabc#33

weibo/spiders/search.py

@@ -1,13 +1,14 @@
 # -*- coding: utf-8 -*-
+import os
 import re
+import sys
 from datetime import datetime, timedelta
 from urllib.parse import unquote
 
 import scrapy
+import weibo.utils.util as util
 from scrapy.exceptions import CloseSpider
 from scrapy.utils.project import get_project_settings
-
-import weibo.utils.util as util
 from weibo.items import WeiboItem
 
 
@@ -16,6 +17,14 @@ class SearchSpider(scrapy.Spider):
     allowed_domains = ['weibo.com']
     settings = get_project_settings()
     keyword_list = settings.get('KEYWORD_LIST')
+    if not isinstance(keyword_list, list):
+        if not os.path.isabs(keyword_list):
+            keyword_list = os.getcwd() + os.sep + keyword_list
+        if not os.path.isfile(keyword_list):
+            print('不存在%s文件' % keyword_list)
+            sys.exit()
+        keyword_list = util.get_keyword_list(keyword_list)
+
     for i, keyword in enumerate(keyword_list):
         if len(keyword) > 2 and keyword[0] == '#' and keyword[-1] == '#':
             keyword_list[i] = '%23' + keyword[1:-1] + '%23'

weibo/utils/util.py

@@ -1,4 +1,4 @@
-
+import sys
 from datetime import datetime, timedelta
 
 from weibo.utils.region import region_dict
@@ -38,6 +38,22 @@ def convert_contain_type(contain_type):
     return '&suball=1'
 
 
+def get_keyword_list(file_name):
+    """获取文件中的关键词列表"""
+    with open(file_name, 'rb') as f:
+        try:
+            lines = f.read().splitlines()
+            lines = [line.decode('utf-8-sig') for line in lines]
+        except UnicodeDecodeError:
+            print(u'%s文件应为utf-8编码，请先将文件编码转为utf-8再运行程序', file_name)
+            sys.exit()
+        keyword_list = []
+        for line in lines:
+            if line:
+                keyword_list.append(line)
+    return keyword_list
+
+
 def get_regions(region):
     """根据区域筛选条件返回符合要求的region"""
     new_region = {}
@@ -68,7 +84,7 @@ def standardize_date(created_at):
         created_at = (datetime.now() - hour).strftime("%Y-%m-%d %H:%M")
     elif "今天" in created_at:
         today = datetime.now().strftime('%Y-%m-%d')
-        created_at = today+' '+created_at[2:]
+        created_at = today + ' ' + created_at[2:]
     elif '年' not in created_at:
         year = datetime.now().strftime("%Y")
         month = created_at[:2]