更新图片5

baike/spiders/baike.py

@@ -15,6 +15,8 @@ if not os.path.exists('logs/'):
     os.mkdir('logs/')
 logging.basicConfig(filename=f'logs/{logfile_name}.log', filemode='a+',
                     format='%(levelname)s - %(asctime)s - %(message)s', datefmt='%d-%b-%y %H:%M:%S')
+
+
 class BaikeSpider(scrapy.Spider):
     name = 'baike'
     allowed_domains = ['baike.baidu.com']
@@ -79,9 +81,8 @@ class BaikeSpider(scrapy.Spider):
                         '//dt//text()').getall()
                     attr = ''.join(temp).replace('\xa0', '')
                     # value
-                    values = Selector(text=value).xpath(
-                        '//dd/text()|//dd/a//text()').getall()
-                    for value in values:
+                    value = ''.join(Selector(text=value).xpath(
+                        '//dd/text()|//dd/a//text()').getall())
                     try:
                         value = value.replace('\n', '')
                         logging.warning(entity+'_'+attr+'_'+value)
@@ -93,6 +94,8 @@ class BaikeSpider(scrapy.Spider):
                         )
                     except pymongo.errors.DuplicateKeyError:
                         pass
-                        session.write_transaction(self.add_node, entity, attr, value)
+                    session.write_transaction(
+                        self.add_node, entity, attr, value)
             except Exception:
-                logging.error('\n---'.join(attrs)+'\n_________________'+'\n---'.join(values))
+                logging.error('\n---'.join(attrs) +
+                              '\n_________________'+'\n---'.join(values))