These regular expressions where all wrong

FourmiCrawler/sources/ChemSpider.py

···
+import re
+
 from scrapy import log
 from scrapy.http import Request
 from scrapy.selector import Selector
···
 from source import Source
 from FourmiCrawler.items import Result
 
-import re
 
 # [TODO] - Maybe clean up usage of '.extract()[0]', because of possible IndexError exception.
 
···
     somewhere.
     """
 
-    website = 'http://www.chemspider.com/*'
+    website = 'http://www\.chemspider\.com/.*'
 
     search = 'Search.asmx/SimpleSearch?query=%s&token='
     structure = 'Chemical-Structure.%s.html'
···
         """
         if compound in self.ignore_list or self.cfg['token'] == '':
             return None
-        searchurl = self.website[:-1] + self.search % compound
+        searchurl = self.website[:-2] + self.search % compound
         log.msg('chemspider compound', level=log.DEBUG)
         return Request(url=searchurl, callback=self.parse_searchrequest)

FourmiCrawler/sources/NIST.py

···
     This plugin manages searching for a chemical on the NIST website
     and parsing the resulting page if the chemical exists on NIST.
     """
-    website = "http://webbook.nist.gov/*"
+    website = "http://webbook\.nist\.gov/.*"
 
     search = 'cgi/cbook.cgi?Name=%s&Units=SI&cTP=on'
 
···
         """
         if compound not in self.ignore_list:
             self.ignore_list.update(compound)
-            return Request(url=self.website[:-1] + self.search % compound,
+            return Request(url=self.website[:-2] + self.search % compound,
                            callback=self.parse)

FourmiCrawler/sources/PubChem.py

···
+import re
+
 from scrapy.http import Request
 from scrapy import log
-from source import Source
 from scrapy.selector import Selector
+
+from source import Source
 from FourmiCrawler.items import Result
-import re
 
 
 class PubChem(Source):
···
     """
 
     #PubChem has its data on compound name, properties and their values on different html pages, so different URLs used
-    website = 'https://*.ncbi.nlm.nih.gov/*'
-    website_www = 'https://www.ncbi.nlm.nih.gov/*'
-    website_pubchem = 'https://pubchem.ncbi.nlm.nih.gov/*'
+    website = 'https://.*\.ncbi\.nlm\.nih\.gov/.*'
+    website_www = 'https://www.ncbi.nlm.nih.gov/.*'
+    website_pubchem = 'https://pubchem.ncbi.nlm.nih.gov/.*'
     search = 'pccompound?term=%s'
     data_url = 'toc/summary_toc.cgi?tocid=27&cid=%s'
 

FourmiCrawler/sources/WikipediaParser.py

···
     It also returns requests with other external sources which contain information on parsed subject.
     """
 
-    website = "http://en.wikipedia.org/wiki/*"
+    website = "http://en\.wikipedia\.org/wiki/.*"
     __spider = None
     searched_compounds = []
 
···
         return items
 
     def new_compound_request(self, compound):
-        return Request(url=self.website[:-1] + compound, callback=self.parse)
+        return Request(url=self.website[:-2] + compound, callback=self.parse)
 
     @staticmethod
     def clean_items(items):

FourmiCrawler/sources/source.py

···
 
 
 class Source:
-    website = "http://something/*"  # Regex of URI's the source is able to parse
+    website = "http://something/.*"  # Regex of URI's the source is able to parse
     _spider = None
 
     def __init__(self, config=None):
···
         :param compound: A compound name.
         :return: A new Scrapy Request
         """
-        # return Request(url=self.website[:-1] + compound, callback=self.parse)
+        # return Request(url=self.website[:-2] + compound, callback=self.parse)
         pass
 
     def set_spider(self, spider):