How do I connect items from one parse method to another? - scrapy

'''
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
...

Related

I want to extract the numbers at the end of a url using regular expressions in scrapy

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.

Scrapy - How to define structure of the csv export (columns,etc..)

I am quite new with scrapy, and i'm to figure out how to set the structure of a csv export. I have in the following example 2 kind of data scraped: ids and links
Here is the simple code i'm using :
class MybotSpider(scrapy.Spider):
name = 'mybot'
start_urls = ['url']
def parse(self, response):
all_dataids = response.css('li::attr(data-id)').extract()
all_links = response.xpath('//a[contains(#class, "js_clickable")]/#href').extract()
adlist = SpiderItem()
adlist['dataid'] = all_dataids
adlist['link'] = all_links
yield adlist
But my export is like this :
instead, i would like to export with for each id corresponding the href and separated in rows :
Make yielding items in this way:
def parse(self, response):
all_dataids = response.css('li::attr(data-id)').extract()
all_links = response.xpath('//a[contains(#class, "js_clickable")]/#href').extract()
for link, dataid in zip(all_links, all_dataids):
adlist = SpiderItem()
adlist['dataid'] = dataid
adlist['link'] = link
yield adlist
Here you zip your arrays to ((link, dataid), (link, dataid), (link, dataid), ...) and then yielding them one by one. So it should give you desired output.

How to fixing different element text to extract

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()

How to use the yield function to scrape data from multiple pages

I'm trying to scrape data from amazon India website. I am not able collect response and parse the elements using the yield() method when:
1) I have to move from product page to review page
2) I have to move from one review page to another review page
Product page
Review page
Code flow:
1) customerReviewData() calls the getCustomerRatingsAndComments(response)
2) The getCustomerRatingsAndComments(response)
finds the URL of the review page and call the yield request method with getCrrFromReviewPage(request) as callback method, with url of this review page
3) getCrrFromReviewPage() gets new response of the firstreview page and scrape all the elements from the first review page (page loaded) and add it to customerReviewDataList[]
4) get URL of the next page if it exists and recursively call getCrrFromReviewPage() method, and crawl elements from next page, until all the review page is crawled
5) All the reviews gets added to the customerReviewDataList[]
I have tried playing around with yield() changing the parameters and also looked up the scrapy documentation for yield() and Request/Response yield
# -*- coding: utf-8 -*-
import scrapy
import logging
customerReviewDataList = []
customerReviewData = {}
#Get product name in <H1>
def getProductTitleH1(response):
titleH1 = response.xpath('normalize-space(//*[#id="productTitle"]/text())').extract()
return titleH1
def getCustomerRatingsAndComments(response):
#Fetches the relative url
reviewRelativePageUrl = response.css('#reviews-medley-footer a::attr(href)').extract()[0]
if reviewRelativePageUrl:
#get absolute URL
reviewPageAbsoluteUrl = response.urljoin(reviewRelativePageUrl)
yield Request(url = reviewPageAbsoluteUrl, callback = getCrrFromReviewPage())
self.log("yield request complete")
return len(customerReviewDataList)
def getCrrFromReviewPage():
userReviewsAndRatings = response.xpath('//div[#id="cm_cr-review_list"]/div[#data-hook="review"]')
for userReviewAndRating in userReviewsAndRatings:
customerReviewData[reviewTitle] = response.css('#cm_cr-review_list .review-title span ::text').extract()
customerReviewData[reviewDescription] = response.css('#cm_cr-review_list .review-text span::text').extract()
customerReviewDataList.append(customerReviewData)
reviewNextPageRelativeUrl = response.css('#cm_cr-pagination_bar .a-pagination .a-last a::attr(href)')[0].extract()
if reviewNextPageRelativeUrl:
reviewNextPageAbsoluteUrl = response.urljoin(reviewNextPageRelativeUrl)
yield Request(url = reviewNextPageAbsoluteUrl, callback = getCrrFromReviewPage())
class UsAmazonSpider(scrapy.Spider):
name = 'Test_Crawler'
allowed_domains = ['amazon.in']
start_urls = ['https://www.amazon.in/Philips-Trimmer-Cordless-Corded-QT4011/dp/B00JJIDBIC/ref=sr_1_3?keywords=philips&qid=1554266853&s=gateway&sr=8-3']
def parse(self, response):
titleH1 = getProductTitleH1(response),
customerReviewData = getCustomerRatingsAndComments(response)
yield{
'Title_H1' : titleH1,
'customer_Review_Data' : customerReviewData
}
I'm getting the following response:
{'Title_H1': (['Philips Beard Trimmer Cordless and Corded for Men QT4011/15'],), 'customer_Review_Data': <generator object getCustomerRatingsAndComments at 0x048AC630>}
The "Customer_review_Data" should be a list of dict of title and review
I am not able to figure out as to what mistake I am doing here.
When I use the log() or print() to see what data is captured in customerReviewDataList[], unable to see the data in the console either.
I am able to scrape all the reviews in customerReviewDataList[], if they are present in the product page,
In this scenario where I have to use the yield function I am getting the output stated above like this [https://ibb.co/kq8w6cf]
This is the kind of output I am looking for:
{'customerReviewTitle': ['Difficult to find a charger adapter'],'customerReviewComment': ['I already have a phillips trimmer which was only cordless. ], 'customerReviewTitle': ['Good Product'],'customerReviewComment': ['Solves my need perfectly HK']}]}
Any help is appreciated. Thanks in advance.
You should complete the Scrapy tutorial. The Following links section should be specially helpful to you.
This is a simplified version of your code:
def data_request_iterator():
yield Request('https://example.org')
class MySpider(Spider):
name = 'myspider'
start_urls = ['https://example.com']
def parse(self, response):
yield {
'title': response.css('title::text').get(),
'data': data_request_iterator(),
}
Instead, it should look like this:
class MySpider(Spider):
name = 'myspider'
start_urls = ['https://example.com']
def parse(self, response):
item = {
'title': response.css('title::text').get(),
}
yield Request('https://example.org', meta={'item': item}, callback=self.parse_data)
def parse_data(self, response):
item = response.meta['item']
# TODO: Extend item with data from this second response as needed.
yield item

crawling inside a for loop is not synchronous

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