Scrapy, only follow internal URLS but extract all links found
An updated code based on 12Ryan12's answer,
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors.lxmlhtml import LxmlLinkExtractor
from scrapy.item import Item, Field
class MyItem(Item):
url= Field()
class someSpider(CrawlSpider):
name = 'crawltest'
allowed_domains = ['someurl.com']
start_urls = ['http://www.someurl.com/']
rules = (Rule(LxmlLinkExtractor(allow=()), callback='parse_obj', follow=True),)
def parse_obj(self,response):
item = MyItem()
item['url'] = []
for link in LxmlLinkExtractor(allow=(),deny = self.allowed_domains).extract_links(response):
item['url'].append(link.url)
return item
You can also use the link extractor to pull all the links once you are parsing each page.
The link extractor will filter the links for you. In this example the link extractor will deny links in the allowed domain so it only gets outside links.
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors import LxmlLinkExtractor
from myproject.items import someItem
class someSpider(CrawlSpider):
name = 'crawltest'
allowed_domains = ['someurl.com']
start_urls = ['http://www.someurl.com/']
rules = (Rule(LxmlLinkExtractor(allow=()), callback='parse_obj', follow=True),)
def parse_obj(self,response):
for link in LxmlLinkExtractor(allow=(),deny = self.allowed_domains).extract_links(response):
item = someItem()
item['url'] = link.url
A solution would be make usage a process_link function in the SgmlLinkExtractor Documentation here http://doc.scrapy.org/en/latest/topics/link-extractors.html
class testSpider(CrawlSpider):
name = "test"
bot_name = 'test'
allowed_domains = ["news.google.com"]
start_urls = ["https://news.google.com/"]
rules = (
Rule(SgmlLinkExtractor(allow_domains=()), callback='parse_items',process_links="filter_links",follow= True) ,
)
def filter_links(self, links):
for link in links:
if self.allowed_domains[0] not in link.url:
print link.url
return links
def parse_items(self, response):
### ...