I am trying to scrape some posts on the primary page where almost everything i need is there. But on the link(ed) page there is a date field I additionally need. I tried a callback with the following:
from scrapy.spider import BaseSpider
from macnn_com.items import MacnnComItem
from scrapy.selector import HtmlXPathSelector
from scrapy.contrib.loader import XPathItemLoader
from scrapy.contrib.loader.processor import MapCompose, Join
from scrapy.http.request import Request
class MacnnSpider(BaseSpider):
name = 'macnn_com'
allowed_domains = ['macnn.com']
start_urls = ['http://www.macnn.com']
posts_list_xpath = '//div[#class="post"]'
item_fields = { 'title': './/h1/a/text()',
'link': './/h1/a/#href',
'summary': './/p/text()',
'image': './/div[#class="post_img"]/div[#class="post_img_border"]/a/img/#original' }
def parse(self, response):
hxs = HtmlXPathSelector(response)
# iterate over posts
for qxs in hxs.select(self.posts_list_xpath):
loader = XPathItemLoader(MacnnComItem(), selector=qxs)
# define processors
loader.default_input_processor = MapCompose(unicode.strip)
loader.default_output_processor = Join()
# skip posts with empty titles
if loader.get_xpath('.//h1/a/text()') == []:
continue
# iterate over fields and add xpaths to the loader
for field, xpath in self.item_fields.iteritems():
loader.add_xpath(field, xpath)
request = Request(loader.get_xpath('.//h1/a/#href')[0], callback=self.parse_link,meta={'loader':loader})
yield request
#loader.add_value('datums',request)
yield loader.load_item()
def parse_link(self, response):
loader = response.meta["loader"]
hxs = HtmlXPathSelector(response)
hero = hxs.select("//div[#class='post_header']/h2/text()").extract()
loader.add_value('datums',hero)
return loader
But I get errors like
ERROR: Spider must return Request, BaseItem or None, got 'XPathItemLoader' in <GET http://www.macnn.com/articles/13/06/14/sidebar.makes.it.easier.to.jump.between.columns/>
What am I doing wrong here?
parse_link needs to return an item, not the loader.
def parse_link(self, response):
loader = response.meta["loader"]
hxs = HtmlXPathSelector(response)
hero = hxs.select("//div[#class='post-header']/h2/text()").extract()
loader.add_value('datums',hero)
return loader.load_item()
Related
I am trying to extract information from Listing and Detail pages.
The code below correctly scrapes the reviewer information from the Listing page and all linked pages (where a contains Next)
The detail_pages Urls are also captured. e.g. http://www.screwfix.com/p/prysmian-6242y-twin-earth-cable-2-5mm-x-100m-grey/20967
However I cannot see how I can navigate to and scrape the information from the Detail pages.
Is there anyone here who used Scrapy successfully who can help me to finish this spider?
Thank you for the help.
I include the code for the spider below:
# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from scrapy.spider import Spider
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import Selector
from hn_scraper.items import HnArticleItem
class ScrewfixSpider(Spider):
name = "Screwfix"
allowed_domains = ["www.screwfix.com"]
start_urls = ('http://www.screwfix.com/', )
link_extractor = SgmlLinkExtractor(
allow=('www', ),
restrict_xpaths=('//a[contains(., "Next")]', ))
detail_page_extractor = SgmlLinkExtractor(
allow=('www', ),
restrict_xpaths=('//tr[#id[contains(., "reviewer")]]/td[3]/a', ))
def extract_one(self, selector, xpath, default=None):
extracted = selector.xpath(xpath).extract()
if extracted:
return extracted[0]
return default
def parse(self, response):
for link in self.link_extractor.extract_links(response):
request = Request(url=link.url)
request.meta.update(link_text=link.text)
yield request
for item in self.parse_item(response):
yield item
def parse_item(self, response):
selector = Selector(response)
rows = selector.xpath('//table[contains(.,"crDataGrid")]//tr[#id[contains(., "reviewer")]]')
for row in rows:
item = HnArticleItem()
reviewer = row.xpath('td[3]/a')
reviewer_url = self.extract_one(reviewer, './#href', '')
reviewer_name = self.extract_one(reviewer, 'b/text()', '')
total_reviews = row.xpath('td[4]/text()').extract()
item['url'] = reviewer_url
item['name'] = reviewer_name
item['total_reviews'] = total_reviews
yield item
detail_pages = self.detail_page_extractor.extract_links(response)
if detail_pages:
print 'detail_pages'
print detail_pages[0].url
yield Request(detail_pages[0].url)
This is my first scraper using scrapy.
I am trying to scrap video url, title from https://www.google.co.in/trends/hotvideos#hvsm=0 site.
import scrapy
from scrapy.item import Item, Field
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
class CraigslistItem(Item):
title = Field()
link = Field()
class DmozSpider(scrapy.Spider):
name = "google"
allowed_domains = ["google.co.in"]
start_urls = [
"https://www.google.co.in/trends/hotvideos#hvsm=0"
]
def parse(self, response):
#for sel in response.xpath('//body/div'):
hxs = HtmlXPathSelector(response)
sites = hxs.xpath("//span[#class='single-video-image-container']")
items = []
for sel in response.xpath("//span[#class='single-video-image-container']"):
item = CraigslistItem()
item['title'] = sel.xpath('a/text()').extract()
item['link'] = sel.xpath('a/#href').extract()
items.append(item)
print items
General walk through of what I am doing wrong would be much appreciable.
Use the help Scrapy FormRequest to get it done.
from scrapy.http import FormRequest
import json
class DmozSpider(scrapy.Spider):
name = "google"
allowed_domains = ["google.co.in"]
start_urls = [
"https://www.google.co.in/trends/hotvideos#hvsm=0"
]
def parse(self, response):
url = 'https://www.google.co.in/trends/hotvideos/hotItems'
formdata = {'hvd':'','geo': 'IN','mob': '0','hvsm': '0'}
yield FormRequest(url=url, formdata=formdata, callback=self.parse_data)
def parse_data(self, response):
json_response = json.loads(response.body)
videos = json_response.get('videoList')
for video in videos:
item = CraigslistItem()
item['title'] = video.get('title')
item['link'] = video.get('url')
yield item
I have a spider written as below, but it doesn't seem to be getting to the function parse. Could someone take a quick look and let me know if I'm missing something. Am I implementing the SgmlLinkExtractor properly?
The spider should pick out all the links from the left sidebar, create a request from them, then parse the next page for a facebook link. It should also do this for other pages as specified in the SgmlLinkExtractor. At the moment, the spider is running, but not parsing any pages.
class PrinzSpider(CrawlSpider):
name = "prinz"
allowed_domains = ["prinzwilly.de"]
start_urls = ["http://www.prinzwilly.de/"]
rules = (
Rule(
SgmlLinkExtractor(
allow=(r'veranstaltungen-(.*)', ),
),
callback='parse'
),
)
def parse(self, response):
hxs = HtmlXPathSelector(response)
startlinks = hxs.select("//ul[#id='mainNav2']/li/a")
print startlinks
for link in startlinks:
giglink = link.select('#href').extract()
item = GigItem()
item['gig_link'] = giglink
request = Request(item['gig_link'], callback='parse_gig_page')
item.meta['item'] = item
yield request
def parse_gig_page(self, response):
hxs = HtmlXPathSelector(response)
item = response.meta['item']
gig_content = hxs.select("//div[#class='n']/table/tbody").extract()
fb_link = re.findall(r'(?:www.facebook.com/)(.*)', gig_content)
print '********** FB LINK ********', fb_link
return item
EDIT **
settings.py
BOT_NAME = 'gigscraper'
SPIDER_MODULES = ['gigscraper.spiders']
NEWSPIDER_MODULE = 'gigscraper.spiders'
ITEM_PIPLINES = ['gigscraper.pipelines.GigscraperPipeline']
items.py
from scrapy.item import Item, Field
class GigItem(Item):
gig_link = Field()
pipelines.py
class GigscraperPipeline(object):
def process_item(self, item, spider):
print 'here I am in the pipeline'
return item
Two problems:
extract() returns a list, you are missing [0]
Request's callback should not be a string, use self.parse_gig_page
Here's the modified code (working):
import re
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.http import Request
from scrapy.item import Item, Field
from scrapy.selector import HtmlXPathSelector
class GigItem(Item):
gig_link = Field()
class PrinzSpider(CrawlSpider):
name = "prinz"
allowed_domains = ["prinzwilly.de"]
start_urls = ["http://www.prinzwilly.de/"]
rules = (Rule(SgmlLinkExtractor(allow=(r'veranstaltungen-(.*)',)), callback='parse'),)
def parse(self, response):
hxs = HtmlXPathSelector(response)
startlinks = hxs.select("//ul[#id='mainNav2']/li/a")
for link in startlinks:
item = GigItem()
item['gig_link'] = link.select('#href').extract()[0]
yield Request(item['gig_link'], callback=self.parse_gig_page, meta={'item': item})
def parse_gig_page(self, response):
hxs = HtmlXPathSelector(response)
item = response.meta['item']
gig_content = hxs.select("//div[#class='n']/table/tbody").extract()[0]
fb_link = re.findall(r'(?:www.facebook.com/)(.*)', gig_content)
print '********** FB LINK ********', fb_link
return item
Hope that helps.
Suppose this is my code
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from dmoz.items import DmozItem
class DmozSpider(BaseSpider):
domain_name = "dmoz.org"
start_urls = [
"http://www.dmoz.org/Computers/Programming/Languages/Python/Books/",
"http://www.dmoz.org/Computers/Programming/Languages/Python/Resources/"
]
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.select('//ul[2]/li')
items = []
for site in sites:
item = DmozItem()
item['title'] = site.select('a/text()').extract()
item['link'] = site.select('a/#href').extract()
item['desc'] = site.select('text()').extract()
items.append(item)
return items
SPIDER = DmozSpider()
If i have used crawlSpider then i could uses Rules to implement thelink extractor but how can i mention rules in base spider. Like in above example. Because rules is only avaialble in crawlspider not base spider
Perhaps you could parse the response for your rule criteria and then pass the successful responses on to a second callback? Pseudo-code below:
def parse(self, response):
# check response for rule criteria
...
if rule:
# create new request to pass to second callback
req = Request("http://www.example.com/follow", callback=self.parse2)
return req
def parse2(self, response):
hxs = HtmlXPathSelector(response)
# do stuff with the successful response
from string import join
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.spiders.crawl import Rule, CrawlSpider
from scrapy.http.request import Request
from scrapy.selector import HtmlXPathSelector
from Gfire.items import GfireItem
class GuideSpider(CrawlSpider):
name = "Gfire"
allowed_domains = ['www.example.com']
start_urls = [
"http://www.example.com/gfire/guides"
]
rules = (
Rule(SgmlLinkExtractor(allow=("gfire/guides.*page=")), callback='parse_item', follow=True),
)
def parse_item(self, response):
hxs = HtmlXPathSelector(response)
items = []
sites = hxs.select('//div[#class="title"]')
for site in sites:
item = GFireItem()
item['title'] = site.select('./a/text()').extract()
item['guide_url'] = site.select('./a/#href').extract()
item['guide_url'] = "http://www.example.com" + join(item['guide_url'])
items.append(item)
return Request(items[1], callback=self.parse_item2)
def parse_item2(self, response):
hxs = HtmlXPathSelector(response)
hero = hxs.select("//h3/a/text()").extract()
return hero
Can't get this spider to work. The request function contains items[1] that should be item['guide_url'] but it says me that the parameter has to be str or unicode.
How can I corret this error? And how can I pass to the callback function the items list? Via request.meta?
Your item[1] is actually an instance of GFireItem.
I'm not certain why you are creating these as you only use one (the second site in your list of sites), discarding the rest of the list.
That aside, you need to extract the items[1]['guide_url'] url when creating the Request:
return Request(items[1]['guide_url'], callback=self.parse_item2)
def parse_item(self, response):
hxs = HtmlXPathSelector(response)
items = []
sites = hxs.select('//div[#class="title"]')
for site in sites:
item = GFireItem()
item['title'] = site.select('./a/text()').extract()
item['guide_url'] = site.select('./a/#href').extract()
item['guide_url'] = "http://www.example.com" + join(item['guide_url'])
items.append(item)
return Request(items[1]['guide_url'], request.meta={'items':items}, callback=self.parse_item2)
def parse_item2(self, response):
items = response.meta["items"]
hxs = HtmlXPathSelector(response)
hero = hxs.select("//h3/a/text()").extract()
return hero