**keyword = ''
'''To obtain keyword'''
def test():`enter code here`
keywords = list()
while True:
print('what do you want to do?(a: add a key word for searching, q:quit adding words and start)')
command = input('command:')
if command == 'a':
word = input('keyword: ')
if word not in keywords:
keywords.append(word)
elif command == 'q':
break
else:
print('please input a valid command')
if len(keywords) == 0:
return
search_string = ''
for keyword in keywords:
search_string += keyword
search_string += '+'
search_string = search_string[:-1]
print(search_string)
search_url = 'http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-' \
'bool.html&r=0&f=S&l=50&TERM1=' + search_string + '&FIELD1=&co1=AND&TERM2=&FIELD2=&d=PTXT'
return search_url
'''Incoming url start the scrapy crawle'''
class Uspto(scrapy.Spider):
name = 'uspto'
#allowed_domains = ['http://patft.uspto.gov/']
#start_url = 'http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=0&f=S&l=50&TERM1=water&FIELD1=&co1=AND&TERM2=&FIELD2=&d=PTXT'
allowed_domains = ["http://patft.uspto.gov"]
keyword = test()
start_urls = [
#"http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&p=1&u=%2Fnetahtml%2FPTO%2Fsearch-bool.html&r=0&f=S&l=50&TERM1=python&FIELD1=&co1=AND&TERM2=&FIELD2=&d=PTXT",
keyword,
]
**
enter image description here Error screenshot
From the keyboard input keywords according to the keyword construction link, then start the crawler, the problem now is my access to the keyword method problems
