Develop Reference

Crawl iframe and page at the same time

I just wanted to know if it's possible to crawl a page on a website and extract data from this page and from an iframe in this page at the same time?
I'm using scrapy with python and I already know how to extract data from the iframe...
Thank you for your help!!
Thanks to your answer, I made this... But I don't know what to put instead of 'url'... Can you help me again please?
# -*- coding: utf-8 -*-
import scrapy
import re
import numbers
from fnac.items import FnacItem
from urllib.request import urlopen
# from scrapy.spiders import CrawlSpider, Rule
# from scrapy.linkextractors import LinkExtractor
from bs4 import BeautifulSoup
class Fnac(CrawlSpider): #scrapy.Spider
name = 'FnacCom'
allowed_domains = ['fnac.com']
start_urls = ['http://www.fnac.com/MORMANE/srefA5533119-3387-5EC4-82B6-AA61216BF599']
##### To extract links in order to run the spider in them
# rules = (
# Rule(LinkExtractor(allow=()), callback='parse'),
# )
def parse(self, response):
soup = BeautifulSoup(urlopen(response.url), "lxml")
iframexx = soup.find_all('iframe')
for iframe in iframexx:
yield scrapy.Request(iframe.attrs['src'],callback=self.parse2)
##### Main function
def parse1(self, response):
item1 = FnacItem()
nb_sales = response.xpath('//table[#summary="données détaillée du vendeur"]/tbody/tr/td/span/text()').extract()
country = response.xpath('//table[#summary="données détaillée du vendeur"]/tbody/tr/td/text()').extract()
yield scrapy.Request(url, meta={'item': item1}) #I don't know what to put instead of URL...
def parse2(self, response):
same_item = response.meta['item']
address = response.xpath('//div/p/text()').re(r'.*Adresse \: (.*)\n?.*')
email = response.xpath('//div/ul/li[contains(text(),"#")]/text()').extract()
name = response.xpath('//div/p[#class="customer-policy-label"]/text()').re(r'Infos sur la boutique \: ([a-zA-Z0-9]*)')
phone = response.xpath('//div/p/text()').re(r'.*Tél \: ([\d]*)\n?.*')
siret = response.xpath('//div/p/text()').re(r'.*Siret \: ([\d]*)\n?.*')
vat = response.xpath('//div/text()').re(r'.*TVA \: (.*)')
if (len(name) != 0):
item['name'] = ''.join(name).strip()
item['address'] = ''.join(address).strip()
item['phone'] = ''.join(phone).strip()
item['email'] = ''.join(email).strip()
item['nb_sales'] = ''.join(nb_sales).strip()
item['country'] = ''.join(country).strip()
item['vat'] = ''.join(vat).strip()
item['siret'] = ''.join(siret).strip()
return item

to combine information from different requests into a similar item, you have to use the meta parameter of the requests:
def parse1(self, response):
item1 = {
...
}
yield Request(url='another_url.com', meta={'item': item1}, callback=self.parse2)
def parse2(self, response):
same_item = response.meta['item']
# keep populating the item with the second response
...
yield same_item

Scrapy: Looping through search results only returns first item

I'm scraping a site by going through the search page, then looping through all results within. However it only seems to be returning the first result for each page. I also don't think it's hitting the start page's results either.
Secondly, the price is returning as some sort of Unicode (£ symbol) - how can I remove it altogether just leaving the price?
'regular_price': [u'\xa38.59'],
Here is the HTML:
http://pastebin.com/F8Lud0hu
Here's the spider:
import scrapy
import random
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy.selector import Selector
from cdl.items import candleItem
class cdlSpider(CrawlSpider):
name = "cdl"
allowed_domains = ["www.xxxx.co.uk"]
start_urls = ['https://www.xxxx.co.uk/advanced_search_result.php']
rules = [
Rule(LinkExtractor(
allow=['advanced_search_result\.php\?sort=2a&page=\d*']),
callback='parse_listings',
follow=True)
]
def parse_listings(self, response):
sel = Selector(response)
urls = sel.css('a.product_img')
for url in urls:
url = url.xpath('#href').extract()[0]
return scrapy.Request(url,callback=self.parse_item)
def parse_item(self, response):
candle = candleItem()
n = response.css('.prod_info_name h1')
candle['name'] = n.xpath('.//text()').extract()[0]
if response.css('.regular_price'):
candle['regular_price'] = response.css('.regular_price').xpath('.//text()').extract()
else:
candle['was_price'] = response.css('.was_price strong').xpath('.//text()').extract()
candle['now_price'] = response.css('.now_price strong').xpath('.//text()').extract()
candle['referrer'] = response.request.headers.get('Referer', None)
candle['url'] = response.request.url
yield candle

Yes it's returning only the first result because of your parse_listing method (you're returning the first url and you should be yielding it). I would do something like:
def parse_listings(self, response):
for url in response.css('a.product_img::attr(href)').extract():
yield Request(url, callback=self.parse_item)
In that case I would even do something like:
class CdlspiderSpider(CrawlSpider):
name = 'cdlSpider'
allowed_domains = ['www.xxxx.co.uk']
start_urls = ['https://www.xxxx.co.uk/advanced_search_result.php']
rules = [
Rule(LinkExtractor(allow='advanced_search_result\.php\?sort=2a&page=\d*')),
Rule(LinkExtractor(restrict_css='a.product_img'), callback='parse_item')
]
def parse_item(self, response):
...
if response.css('.regular_price'):
candle['regular_price'] = response.css('.regular_price::text').re_first(r'\d+\.?\d*')
else:
candle['was_price'] = response.css('.was_price strong::text').re_first(r'\d+\.?\d*')
candle['now_price'] = response.css('.now_price strong::text').re_first(r'\d+\.?\d*')
...
return candle

To remove the £, just replace it with an empty string like this:
pricewithpound = u'\xa38.59'
price = pricewithpound.replace(u'\xa3', '')
To investigate the scrapy issue, can you please provide the HTML source ?

scrapy SgmlLinkExtractor scrape Master and Detail pages

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)

Scrapy crawl only part of a website

Hello there I have the following code to scan all links in a give site.
from scrapy.item import Field, Item
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors import LinkExtractor
class SampleItem(Item):
link = Field()
class SampleSpider(CrawlSpider):
name = "sample_spider"
allowed_domains = ["domain.com"]
start_urls = ["http://domain.com"]
rules = (
Rule(LinkExtractor(), callback='parse_page', follow=True),
)
def parse_page(self, response):
item = SampleItem()
item['link'] = response.url
return item
If I'like to check only part of a global site how could I do it? I have tried for example to scan only the french part of an international site whose domain is structured as : domain.com/fr/fr. So I have tried doing :
from scrapy.item import Field, Item
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors import LinkExtractor
class SampleItem(Item):
link = Field()
class SampleSpider(CrawlSpider):
name = "sample_spider"
allowed_domains = ["domain.com/fr/fr"]
start_urls = ["http://domain.com/fr/fr"]
rules = (
Rule(LinkExtractor(), callback='parse_page', follow=True),
)
def parse_page(self, response):
item = SampleItem()
item['link'] = response.url
return item
But the spider only returns 3 results instead of thousands. What am I doing wrong?

To crawl only part of a website, you have to use the LinkExtractor. You can get a sample by issueing scrapy genspider -t crawl domain domain.com.
# -*- coding: utf-8 -*-
import scrapy
from scrapy.contrib.linkextractors import LinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule
from test.items import testItem
class DomainSpider(CrawlSpider):
name = 'domain'
allowed_domains = ['domain.com']
start_urls = ['http://www.domain.com/fr/fr']
rules = (
Rule(LinkExtractor(allow=r'fr/'), callback='parse_item', follow=True),
)
def parse_item(self, response):
i = testItem()
#i['domain_id'] = response.xpath('//input[#id="sid"]/#value').extract()
#i['name'] = response.xpath('//div[#id="name"]').extract()
#i['description'] = response.xpath('//div[#id="description"]').extract()
return i

Scraper not finding pages

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.