Python Urlencode
import urllib.parse
query = 'Hellö Wörld@Python'
print(urllib.parse.quote(query))
>> 'Hell%C3%B6%20W%C3%B6rld%40Python'
Precious Pigeon
import urllib.parse
query = 'Hellö Wörld@Python'
print(urllib.parse.quote(query))
>> 'Hell%C3%B6%20W%C3%B6rld%40Python'>>> from urllib.parse import urljoin
>>> urljoin('/media/path/', 'js/foo.js')
'/media/path/js/foo.js'
>>> import urllib
>>> f = { 'eventName' : 'myEvent', 'eventDescription' : 'cool event'}
>>> urllib.urlencode(f)
'eventName=myEvent&eventDescription=cool+event'
import urllib.request
import urllib.parse
import re
url = 'https://www.geeksforgeeks.org/'
values = {'s':'python programming',
'submit':'search'}
data = urllib.parse.urlencode(values)
data = data.encode('utf-8')
req = urllib.request.Request(url, data)
resp = urllib.request.urlopen(req)
respData = resp.read()
paragraphs = re.findall(r'<p>(.*?)</p>',str(respData))
for eachP in paragraphs:
print(eachP)>>> urllib.parse.urlparse("http://example.com/pa/th;param1=foo;param2=bar?name=val#frag")
ParseResult(scheme='http', netloc='example.com', path='/pa/th', params='param1=foo;param2=bar', query='name=val', fragment='frag')
## amazon.py
queries = ['tshirt for men', ‘tshirt for women’]
class AmazonSpider(scrapy.Spider):
def start_requests(self):
for query in queries:
url = 'https://www.amazon.com/s?' + urlencode({'k': query})
yield scrapy.Request(url=url, callback=self.parse_keyword_response)