fixing issue rugantio#62 by eliminating some empty comments that are …

…triggering a bug in the Scrapy library. 'scrapy/scrapy#4477'
Di-ref · Jul 26, 2020 · cfe1092 · cfe1092
1 parent bda7d6a
commit cfe1092
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 7 deletions.
diff --git a/fbcrawl/spiders/comments.py b/fbcrawl/spiders/comments.py
@@ -31,8 +31,6 @@ def __init__(self, *args, **kwargs):
         super().__init__(*args,**kwargs)
 
     def parse_page(self, response):
-        '''
-        '''
         if self.type == 'post':
             yield scrapy.Request(url=response.url,
                                  callback=self.parse_post,

diff --git a/fbcrawl/spiders/fbcrawl.py b/fbcrawl/spiders/fbcrawl.py
@@ -142,9 +142,9 @@ def parse_page(self, response):
         Parse the given page selecting the posts.
         Then ask recursively for another page.
         '''
-#        #open page in browser for debug
-#        from scrapy.utils.response import open_in_browser
-#        open_in_browser(response)
+        #open page in browser for debug
+        #from scrapy.utils.response import open_in_browser
+        #open_in_browser(response)
 
         #select all posts
         for post in response.xpath("//div[contains(@data-ft,'top_level_post_id')]"):     

diff --git a/fbcrawl/spiders/profiles.py b/fbcrawl/spiders/profiles.py
@@ -32,8 +32,6 @@ def __init__(self, *args, **kwargs):
         super().__init__(*args,**kwargs)
 
     def parse_page(self, response):
-        '''
-        '''
         if self.type == 'post':
             yield scrapy.Request(url=response.url,
                                  callback=self.parse_post,