I'm trying to scrape a fairly straightforward website with a Scrapy BaseSpider since I know in advance where all of the links that I want to crawl are.
The basic layout of the site to be crawled is
List of States
List of Counties within a State
List of agencies within a County
Information about a single agency
I can successfully navigate and get data at all 4 levels, however, my county field is not being populated correctly. For a given agency, instead of the actual county it is in, I get the last county in the State the agency is located in.
Example:
OH - County #3 - Agency #1 (should be County #1)
OH - County #3 - Agency #2 (should be County #2)
OH - County #3 - Agency #3 (correct)
Can't seem to figure out something that I think is relatively simple.
Here's the code:
from scrapy.spider import BaseSpider
from scrapy.selector import Selector
from agencyspider.items import AgencyItem
from scrapy.http import Request
class BasicspiderSpider(BaseSpider):
name = "basicSpider"
allowed_domains = ["usacops.com"]
start_urls = [
'http://www.usacops.com/',
]
items = {}
def parse(self, response):
sel = Selector(response)
states = sel.xpath('//comment()[.=" Begin State Names "]/following::table[1]/tr/td/a')
for s in states:
item = AgencyItem()
state = s.xpath('text()').extract()[0]
url = s.xpath('#href').extract()[0]
item['state'] = state
item['stateUrl']= url
yield Request(url=url,callback=self.parse_counties,meta={'item':item})
def parse_counties(self, response):
sel = Selector(response)
counties = sel.xpath('//comment()[.=" Begin Counties "]/following::table[1]/tr/td/font/a | //comment()[.=" Begin Counties "]/following::table[1]/tr/td/a')
for c in counties:
item = response.request.meta["item"]
county = c.xpath('text()').extract()[0]
countyUrl = c.xpath('#href').extract()[0]
url = item["stateUrl"] + countyUrl
item["county"]=county
item["countyUrl"]=url
yield Request(url=url, callback=self.parse_agencies,meta={'item':item})
def parse_agencies(self,response):
sel = Selector(response)
agencies = sel.xpath('//table[9]/tr/td/table[2]/tr/td/font/a | //table[9]/tr/td/table[2]/tr/td/a')
for a in agencies:
item = response.request.meta["item"]
agency = a.xpath('text()').extract()[0]
agencyUrl = a.xpath('#href').extract()[0]
url = item["stateUrl"] + agencyUrl
item["agency"] = agency
item["agencyUrl"] = url
yield Request(url=url, callback=self.parse_agencyinfo,meta={'item':item})
def parse_agencyinfo(self,response):
sel = Selector(response)
item = response.request.meta["item"]
item["agency"]= ' '.join(sel.xpath('//comment()[.=" Begin center section "]/following::table/tr/td/strong/font[1]/text()').extract())
item["admintype"]= ' '.join(sel.xpath('//comment()[.=" Begin center section "]/following::table/tr/td/strong/font[2]/text()').extract())
item["adminhead"]= ' '.join(sel.xpath('//comment()[.=" Begin center section "]/following::table/tr/td/strong/font[3]/text()[1]').extract())
item["address"]= ' '.join(sel.xpath('//comment()[.=" Begin center section "]/following::table/tr/td/strong/font[3]/text()[position()>1]').extract())
return item
Hey so the problem is every time you assign item = response.request.meta["item"] your referencing and assigning the same item over and over again.
Fortunately its an easy fix! Just wrap response.request.meta["item"] with AgencyItem(response.request.meta["item"]) to create a copy of the state item for each county.
Also don't forget to do the same in other callbacks or else you'll have the problem with other fields. Hope that helps!
Related
'''
import scrapy
from ..items import GooddealItem
class FarmtoolsSpider(scrapy.Spider):
name = 'farmtools'
allowed_domains = ['www.gooddeal.com']
start_urls = ['https://www.gooddeal.com/all?
source=private&sort=publishdate%20desc']
def parse(self, response):
items = GooddealItem()
rows = response.xpath('//ul[#class="card-collection"]/li')
for row in rows:
link = row.xpath('.//a/#href').get() #this is the full link.
link_split = link.split('/')[-1] #this splits the url link th first time.
linkid = link_split.split('?')[0] #this splits it the second time.
title = row.xpath('.//div[1]/p[#class="card__body-title"]/text()').get()
county = row.xpath('.//a/div/div[2]/div[1]/ul[#class="card__body-keyinfo"]/li[contains(text(),"min")]/following-sibling::node()/text()').get()
price = row.xpath('.//p[#class="card__price"]/span[1]/text()').get()
subcat = row.xpath('.//a/div/div[2]/div[1]/p[2]/text()[2]').get()
zero = row.xpath('.//a/div/div[2]/div[1]/ul[#class="card__body-keyinfo"]/li[contains(text(),"min")]/text()').get()
if zero == '0 min':
items['linkid'] = linkid
items['title'] = title
items['county'] = county
items['price'] = price
items['subcat'] = subcat
items['zero'] = zero
items['link'] = link
yield response.follow(url = link, callback=self.parse_item_page)
def parse_item_page(self, response):
items = GooddealItem()
rows = response.xpath('/html/body[1]')
for row in rows:
category = row.xpath('.//main/div/div[1]/div/div[1]/div/nav/span/a[1]/span/text()').get(),
views = row.xpath('.//main/div/div[1]/div/div[2]/div[2]/div[1]/div[3]/div[1]/div/div[1]/div/div/span[2]/text()').get(),
seller_id = row.xpath('.//main/div/div[1]/div/div[2]/div[2]/div[2]/div[3]/div/div[1]/div[1]/div[2]/a/#href').get(),
seller_ads = row.xpath('.//main/div/div[1]/div/div[2]/div[2]/div[2]/div[3]/div/div[2]/div/dl[3]/dd/text()').get(),
lifetime_ads = row.xpath('//main/div/div[1]/div/div[2]/div[2]/div[2]/div[3]/div/div[2]/div/dl[4]/dd/text()').get()
items['category'] = category
items['views'] = views
items['seller_id'] = seller_id
items['seller_ads'] = seller_ads
items['lifetime_ads'] = lifetime_ads
yield items
'''
I'm stuck on this as it's my first attempt. When I run the code I'm just getting back:
2020-07-12 22:53:21 [scrapy.core.scraper] DEBUG: Scraped from <200 https://www.gooddeal.com/dogs-for-sale/dachshunds/25348559>
{'category': (None,),
'lifetime_ads': None,
'seller_ads': (None,),
'seller_id': (None,),
'views': (None,)}
Any help will be appreciated, thanks
I'm assuming you want the data scraped in parse method to be joined together with the data scraped in the parse_item_page.
If you are using Scrapy v1.7+ you can use cb_kwargs when building the request.
This parameter receives a dict with arbitrary data that will be used as argument in the callback function. So you would have to do something like this in your request:
...
yield response.follow(url = link, callback=self.parse_item_page, cb_kwargs={'scraped_item': items})
For this to work, you also need to change the callback function to receive this parameter. Like this:
def parse_item_page(self, response, scraped_item):
...
Scrapy will take care of sending the scraped_item when calling the parse_item_page.
If you are using Scrapy v1.6 or older:
You will need to use the meta parameter. This method still works in more recent versions, but cb_kwargs(solution above) are preferable.
When building the request you will use the meta parameter to include some arbitrary data in the request. The data will be accessible in the response object that the callback function receives. Your request should look like this:
...
yield response.follow(url = link, callback=self.parse_item_page, meta={'scraped_item': items})
In this case you will access the data by calling response.meta:
def parse_item_page(self, response):
items = response.meta.get('scraped_item') #response.meta is a dict
...
I want to get '25430989' from the end of this url.
https://www.example.com/cars-for-sale/2007-ford-focus-1-6-diesel/25430989
How would I write it using the xpath?
I get the link using this xpath:
link = row.xpath('.//a/#href').get()
When I use a regex tester I can isolate it with r'(\d+)$ but when I put it into my code it doesn't work for some reason.
import scrapy
import re
from ..items import DonedealItem
class FarmtoolsSpider(scrapy.Spider):
name = 'farmtools'
allowed_domains = ['www.donedeal.ie']
start_urls = ['https://www.donedeal.ie/all?source=private&sort=publishdate%20desc']
def parse(self, response):
items = DonedealItem()
rows = response.xpath('//ul[#class="card-collection"]/li')
for row in rows:
if row.xpath('.//ul[#class="card__body-keyinfo"]/li[contains(text(),"0 min")]/text()'):
link = row.xpath('.//a/#href').get() #this is the full link.
linkid = link.re(r'(\d+)$).get()
title = row.xpath('.//p[#class="card__body-title"]/text()').get()
county = row.xpath('.//li[contains(text(),"min")]/following-sibling::node()/text()').get()
price = row.xpath('.//p[#class="card__price"]/span[1]/text()').get()
subcat = row.xpath('.//a/div/div[2]/div[1]/p[2]/text()[2]').get()
items['link'] = link
items['linkid'] = linkid
items['title'] = title
items['county'] = county
items['price'] = price
items['subcat'] = subcat
yield items
I'm trying to get the linkid.
The problem is here
link = row.xpath('.//a/#href').get() #this is the full link.
linkid = link.re(r'(\d+)$).get()
When you use the .get() method it returns a string that is saved in the link variable, and strings don't have a .re() method for you to call. You can use one of the methods from the re module (docs for reference).
I would use re.findall(), it will return you a list of values that matches the regex (in this case only one item would return), or None if nothing matches. re.search() is also a good choice, but will return you an re.Match object.
import re #Don't forget to import it
...
link = row.xpath('.//a/#href').get()
linkid = re.findall(r'(\d+)$', link)
Now, the Scrapy selectors also support regex, so an alternative would be implementing it like this: (No need for re module)
linkid = row.xpath('.//a/#href').re_first(r'(\d+)$')
Notice I didn't use .get() there.
I'm setting up a new scrapy spider and developed
I am using windows 10 and it's running.
My problem is extracting text from different element. This elements sometime on (strong tag, p,) sometime have class , sometime have id but i need to implement to one element to extracting a row text.
Please checkout the link of site
https://exhibits.otcnet.org/otc2019/Public/eBooth.aspx?IndexInList=404&FromPage=Exhibitors.aspx&ParentBoothID=&ListByBooth=true&BoothID=193193&fromFeatured=1
https://exhibits.otcnet.org/otc2019/Public/eBooth.aspx?IndexInList=0&FromPage=Exhibitors.aspx&ParentBoothID=&ListByBooth=true&BoothID=202434
https://exhibits.otcnet.org/otc2019/Public/eBooth.aspx?IndexInList=1218&FromPage=Exhibitors.aspx&ParentBoothID=&ListByBooth=true&BoothID=193194&fromFeatured=1
https://prnt.sc/nkl1vc,
https://prnt.sc/nkl1zy,
https://prnt.sc/nkl247,
# -*- coding: utf-8 -*-
import scrapy
class OtcnetSpider(scrapy.Spider):
name = 'otcnet'
# allowed_domains = ['otcnet.org']
start_urls = ['https://exhibits.otcnet.org/otc2019/Public/Exhibitors.aspx?Index=All&ID=26006&sortMenu=107000']
def parse(self, response):
links = response.css('a.exhibitorName::attr(href)').extract()
for link in links:
ab_link = response.urljoin(link)
yield scrapy.Request(ab_link, callback=self.parse_p)
def parse_p(self, response):
url = response.url
Company = response.xpath('//h1/text()').extract_first()
if Company:
Company = Company.strip()
Country = response.xpath('//*[#class="BoothContactCountry"]/text()').extract_first()
State = response.xpath('//*[#class="BoothContactState"]/text()').extract_first()
if State:
State = State.strip()
Address1 = response.xpath('//*[#class="BoothContactAdd1"]/text()').extract_first()
City = response.xpath('//*[#class="BoothContactCity"]/text()').extract_first()
if City:
City = City.strip()
zip_c = response.xpath('//*[#class="BoothContactZip"]/text()').extract_first()
Address = str(Address1)+' '+str(City)+' '+str(State)+' '+str(zip_c)
Website = response.xpath('//*[#id="BoothContactUrl"]/text()').extract_first()
Booth = response.css('.eBoothControls li:nth-of-type(1)::text').extract_first().replace('Booth: ','')
Description = ''
Products = response.css('.caption b::text').extract()
Products= ', '.join(Products)
vid_bulien = response.css('.aa-videos span.hidden-md::text').extract_first()
if vid_bulien=="Videos":
vid_bulien = "Yes"
else:
vid_bulien = "No"
Video_present = vid_bulien
Conference_link = url
Categories = response.css('.ProductCategoryLi a::text').extract()
Categories = ', '.join(Categories)
Address = Address.replace('None','')
yield {
'Company':Company,
'Country':Country,
'State':State,
'Address':Address,
'Website':Website,
'Booth':Booth,
'Description':Description,
'Products':Products,
'Video_present':Video_present,
'Conference_link':Conference_link,
'Categories':Categories
}
I expect the output would be a row description from different element
According to this post and excellent #dimitre-novatchev answer you need to find a node-set intersection:
$ns1 for your page is:
//p[#class="BoothProfile"]/following-sibling::p
$ns2 is:
p[#class="BoothProfile"]/following-sibling::div[1]/preceding-sibling::p
as a result you need to process these p elements:
//p[#class="BoothProfile"]/following-sibling::p[count(.|//p[#class="BoothProfile"]/following-sibling::div[1]/preceding-sibling::p) = count(//p[#class="BoothProfile"]/following-sibling::div[1]/preceding-sibling::p)]
You can use this Scrapy code:
for p_elem in response.xpath('//p[#class="BoothProfile"]/following-sibling::p[count(.|//p[#class="BoothProfile"]/following-sibling::div[1]/preceding-sibling::p) = count(//p[#class="BoothProfile"]/following-sibling::div[1]/preceding-sibling::p)]'):
# using string() to stringify <p>
Description += p_elem.xpath('string(.)').extract_first()
I need to scrape the items of the first page and then go to the next button to go to the second page and scrape and so on.
This is my code, but only scrape the first item of each page, if there are 20 pages enter to every page and scrape only the first item.
Could anyone please help me .
Thank you
Apologies for my english.
class CcceSpider(CrawlSpider):
name = 'ccce'
item_count = 0
allowed_domain = ['www.example.com']
start_urls = ['https://www.example.com./afiliados value=&categoria=444&letter=']
rules = {
# Reglas Para cada item
Rule(LinkExtractor(allow = (), restrict_xpaths = ('//li[#class="pager-next"]/a')), callback = 'parse_item', follow = True),
}
def parse_item(self, response):
ml_item = CcceItem()
#info de producto
ml_item['nombre'] = response.xpath('normalize-space(//div[#class="news-col2"]/h2/text())').extract()
ml_item['url'] = response.xpath('normalize-space(//div[#class="website"]/a/text())').extract()
ml_item['correo'] = response.xpath('normalize-space(//div[#class="email"]/a/text())').extract()
ml_item['descripcion'] = response.xpath('normalize-space(//div[#class="news-col4"]/text())').extract()
self.item_count += 1
if self.item_count > 5:
#insert_table(ml_item)
raise CloseSpider('item_exceeded')
yield ml_item
As you haven't given an working target url, I'm a bit guessing here, but most probably this is the problem:
parse_item should be a parse_page (and act accordingly)
Scrapy is downloading a full page which has - according to your description - multiple items and then passes this as a response object to your parse method.
It's your parse method's responsibility to process the whole page by iterating over the items displayed on the page and creating multiple scraped items accordingly.
The scrapy documentation has several good examples for this, one is here: https://doc.scrapy.org/en/latest/topics/selectors.html#working-with-relative-xpaths
Basically your code structure in def parse_XYZ should look like this:
def parse_page(self, response):
items_on_page = response.xpath('//...')
for sel_item in items_on_page:
ml_item = CcceItem()
#info de producto
ml_item['nombre'] = # ...
# ...
yield ml_item
Insert the right xpaths for getting all items on the page and adjust your item xpaths and you're ready to go.
Source Code
for hotel in response.xpath('//div[contains(#class,"sr_item")]'):
hotelName = hotel.xpath('.//span[contains(#class,"sr-hotel__name")]//text()')
print hotelName.extract()
hotel_image = hotel.xpath('.//img[contains(#class, "hotel_image")]//#src')
print hotel_image.extract()
hotelLink = hotel.xpath('.//a[contains(#class,"hotel_name_link")]//#href')
yield scrapy.Request(response.urljoin(hotelLink[0].extract()), self.parseHotel)
next_page = response.xpath('//a[contains(#class,"paging-next")]//#href')
My code can be seen attached as an image. As, you can see, inside the for loop. I want Scrapy to return from the function "hotelParse", then continue, executing the for loop.
However, now, it firsts prints all the hotel names, meaning, the for loop get executed completely, then "hotelParse" starts yielding.
This would mess up my output, once, I start assigning values to the item object.
Almost definitely what you're trying to do is the "Passing additional data to callback functions" from the Scrapy documentation. Here's how it would look for your case:
def parse_item(self, response):
for hotel in response.xpath('//div[contains(#class,"sr_item")]'):
item = HotelItem()
hotelName = hotel.xpath('.//span[contains(#class,"sr-hotel__name")]//text()')
print hotelName.extract()
item["hotelName"] = hotelName
hotel_image = hotel.xpath('.//img[contains(#class, "hotel_image")]//#src')
print hotel_image.extract()
item["hotel_image"] = hotel_image
hotelLink = hotel.xpath('.//a[contains(#class,"hotel_name_link")]//#href')
request = scrapy.Request(response.urljoin(hotelLink[0].extract()), self.parseHotel)
request.meta['item'] = item
yield request
next_page = response.xpath('//a[contains(#class,"paging-next")]//#href')
yield scrapy.Request(response.urljoin(next_page.extract()), self.parse_item)
def parseHotel(self, response):
item = response.meta['item']
item["extra_1"] = response.xpath('/example/text()').extract_first()
item["extra_2"] = response.xpath('/example2/text()').extract_first()
yield item