I have this simple scrappy code. However get this error when i use response.urljoin(port_homepage_url)
this portion of the code.
import re
import scrapy
from vesseltracker.items import VesseltrackerItem
class GetVessel(scrapy.Spider):
name = "getvessel"
allowed_domains = ["marinetraffic.com"]
start_urls = [
'http://www.marinetraffic.com/en/ais/index/ports/all/flag:AE',
]
def parse(self, response):
item = VesseltrackerItem()
for ports in response.xpath('//table/tr[position()>1]'):
item['port_name'] = ports.xpath('td[2]/a/text()').extract()
port_homepage_url = ports.xpath('td[7]/a/@href').extract()
port_homepage_url = response.urljoin(port_homepage_url)
yield scrapy.Request(port_homepage_url, callback=self.parse, meta={'item': item})
What could be wrong?
Here is the error log.
2016-09-30 17:17:13 [scrapy] DEBUG: Crawled (200) <GET http://www.marinetraffic.com/robots.txt> (referer: None)
2016-09-30 17:17:14 [scrapy] DEBUG: Crawled (200) <GET http://www.marinetraffic.com/en/ais/index/ports/all/flag:AE> (referer: None)
2016-09-30 17:17:14 [scrapy] ERROR: Spider error processing <GET http://www.marinetraffic.com/en/ais/index/ports/all/flag:AE> (referer: None)
Traceback (most recent call last):
File "/Users/noussh/python/env/lib/python2.7/site-packages/scrapy/utils/defer.py", line 102, in iter_errback
yield next(it)
File "/Users/noussh/python/env/lib/python2.7/site-packages/scrapy/spidermiddlewares/offsite.py", line 29, in process_spider_output
for x in result:
File "/Users/noussh/python/env/lib/python2.7/site-packages/scrapy/spidermiddlewares/referer.py", line 22, in <genexpr>
return (_set_referer(r) for r in result or ())
File "/Users/noussh/python/env/lib/python2.7/site-packages/scrapy/spidermiddlewares/urllength.py", line 37, in <genexpr>
return (r for r in result or () if _filter(r))
File "/Users/noussh/python/env/lib/python2.7/site-packages/scrapy/spidermiddlewares/depth.py", line 58, in <genexpr>
return (r for r in result or () if _filter(r))
File "/Users/noussh/python/vesseltracker/vesseltracker/spiders/marinetraffic.py", line 19, in parse
port_homepage_url = response.urljoin(port_homepage_url)
File "/Users/noussh/python/env/lib/python2.7/site-packages/scrapy/http/response/text.py", line 78, in urljoin
return urljoin(get_base_url(self), url)
File "/usr/local/Cellar/python/2.7.12/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urlparse.py", line 261, in urljoin
urlparse(url, bscheme, allow_fragments)
File "/usr/local/Cellar/python/2.7.12/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urlparse.py", line 143, in urlparse
tuple = urlsplit(url, scheme, allow_fragments)
File "/usr/local/Cellar/python/2.7.12/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urlparse.py", line 176, in urlsplit
cached = _parse_cache.get(key, None)
TypeError: unhashable type: 'list'
The ports.xpath('td[7]/a/@href').extract()
returns a list and when you try to do the "urljoin" on it, it fails. Use extract_first()
instead:
port_homepage_url = ports.xpath('td[7]/a/@href').extract_first()
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With