diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py index 93196413c7ef16160fb8e528eeb24f4514074436..1694ffa1d97ea06d702c93bc1642a130a5840dd2 100644 --- a/src/caoscrawler/crawl.py +++ b/src/caoscrawler/crawl.py @@ -239,7 +239,8 @@ class Crawler(object): elif len(crawler_definitions) == 2: crawler_definition = crawler_definitions[1] else: - raise RuntimeError("Crawler definition must not contain more than two documents.") + raise RuntimeError( + "Crawler definition must not contain more than two documents.") # TODO: at this point this function can already load the cfood schema extensions # from the crawler definition and add them to the yaml schema that will be @@ -443,7 +444,8 @@ class Crawler(object): items = [items] self.run_id = uuid.uuid1() - local_converters = Crawler.initialize_converters(crawler_definition, converter_registry) + local_converters = Crawler.initialize_converters( + crawler_definition, converter_registry) # This recursive crawling procedure generates the update list: self.target_data: List[db.Record] = [] self._crawl(items, @@ -525,7 +527,7 @@ class Crawler(object): if (isinstance(p.value, list)): for el in p.value: if (isinstance(el, db.Entity) and el.id is None - and self.get_identified_record_from_local_cache(el) is None): + and self.get_identified_record_from_local_cache(el) is None): return False if (isinstance(p.value, db.Entity) and p.value.id is None and self.get_identified_record_from_local_cache(p.value) is None):