Develop Reference

Extracting next page and setting a break

I'm trying to extract webpage data and wished to take the next few pages also but up to a limit, which I can alter. However, I've tested to see if I can at least extract the next few web-pages using Scrapy (As I'm trying to figure this out in Scrapy to learn it), but It only returns the items within the first page.
How do I extract the next pages while setting a limit i.e. 5 pages
For example, here's what I have tried:
import scrapy
from scrapy.item import Field
from itemloaders.processors import TakeFirst
from scrapy.crawler import CrawlerProcess
class StatisticsItem(scrapy.Item):
ebay_div = Field(output_processor=TakeFirst())
url = Field(output_processor=TakeFirst())
class StatisticsSpider(scrapy.Spider):
name = 'ebay'
start_urls = ['https://www.ebay.com/b/Collectible-Card-Games-Accessories/2536/bn_1852210?rt=nc&LH_BIN=1' +
'&LH_PrefLoc=2&mag=1&_sop=16']
def start_requests(self):
for url in self.start_urls:
yield scrapy.Request(
url
)
def parse(self, response):
all_cards = response.xpath('//div[#class="s-item__wrapper clearfix"]')
for card in all_cards:
name = card.xpath('.//h3/text()').get() #get name of product
price = card.xpath('.//span[#class="s-item__price"]//text()').get() #price
product_url = card.xpath('.//a[#class="s-item__link"]//#href').get() #link to product
# now do whatever you want, append to dictionary, yield as item...
summary_data = {
"Name": name,
"Price": price,
"URL": product_url
}
data = {'summary_data': summary_data}
yield scrapy.Request(product_url, meta=data, callback=self.parse_product_details)
# get the next page
next_page_url = card.xpath('.//a[#class="pagination__next icon-link"]/#href').extract_first()
# The last page do not have a valid url and ends with '#'
if next_page_url == None or str(next_page_url).endswith("#"):
self.log("eBay products collected successfully !!!")
else:
print('\n' + '-' * 30)
print('Next page: {}'.format(next_page_url))
yield scrapy.Request(next_page_url, callback=self.parse)
def parse_product_details(self, response):
# Get the summary data
data = response.meta['summary_data']
data['location'] = response.xpath('//span[#itemprop="availableAtOrFrom"]/text()').extract_first()
yield data
process = CrawlerProcess(
settings={
'FEED_URI': 'collectible_cards.json',
'FEED_FORMAT': 'jsonlines'
}
)
process.crawl(StatisticsSpider)
process.start()

You can try like this first make urls then start start_requests
start_urls = ["https://www.ebay.com/b/Collectible-Card-Games-Accessories/2536/bn_1852210?LH_BIN=1&LH_PrefLoc=2&mag=1&rt=nc&_pgn={}&_sop=16".format(i) for i in range(1,5)]

Web Scraping all Urls from a website with Scrapy and Python

I am writing a web scraper to fetch a group of links
(located at tree.xpath('//div[#class="work_area_content"]/a/#href')
from a website and return the Title and Url of all the leafs sectioned by the leafs parent. I have two scrapers: one in python and one in Scrapy for Python. What is the purpose of callbacks in the Scrapy Request method? Should the information be in a multidimensional or single dimension list ( I believe multi-dimensional but it enhances complication)? Which of the below code is better? If the scraper code is better, how do I migrate the python code to the Scrapy code?
From what I understand from callbacks is that it passes a function's arguments to another function; however, if the callback refers to itself, the data gets overwritten and therefore lost, and you're unable to go back to the root data. Is this correct?
python:
url_storage = [ [ [ [] ] ] ]
page = requests.get('http://1.1.1.1:1234/TestSuites')
tree = html.fromstring(page.content)
urls = tree.xpath('//div[#class="work_area_content"]/a/#href').extract()
i = 0
j = 0
k = 0
for i, url in enumerate(urls):
absolute_url = "".join(['http://1.1.1.1:1234/', url])
url_storage[i][j][k].append(absolute_url)
print(url_storage)
#url_storage.insert(i, absolute_url)
page = requests.get(url_storage[i][j][k])
tree2 = html.fromstring(page.content)
urls2 = tree2.xpath('//div[#class="work_area_content"]/a/#href').extract()
for j, url2 in enumerate(urls2):
absolute_url = "".join(['http://1.1.1.1:1234/', url2])
url_storage[i][j][k].append(absolute_url)
page = requests.get(url_storage[i][j][k])
tree3 = html.fromstring(page.content)
urls3 = tree3.xpath('//div[#class="work_area_content"]/a/#href').extract()
for k, url3 in enumerate(urls3):
absolute_url = "".join(['http://1.1.1.1:1234/', url3])
url_storage[i][j][k].append(absolute_url)
page = requests.get(url_storage[i][j][k])
tree4 = html.fromstring(page.content)
urls3 = tree4.xpath('//div[#class="work_area_content"]/a/#href').extract()
title = tree4.xpath('//span[#class="page_title"]/text()').extract()
yield Request(url_storage[i][j][k], callback=self.end_page_parse_TS, meta={"Title": title, "URL": urls3 })
#yield Request(absolute_url, callback=self.end_page_parse_TC, meta={"Title": title, "URL": urls3 })
def end_page_parse_TS(self, response):
print(response.body)
url = response.meta.get('URL')
title = response.meta.get('Title')
yield{'URL': url, 'Title': title}
def end_page_parse_TC(self, response):
url = response.meta.get('URL')
title = response.meta.get('Title')
description = response.meta.get('Description')
description = response.xpath('//table[#class="wiki_table]/tbody[contains(/td/text(), "description")/parent').extract()
yield{'URL': url, 'Title': title, 'Description':description}
Scrapy:
# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractor import LinkExtractor
from scrapy.spiders import Rule, CrawlSpider
from datablogger_scraper.items import DatabloggerScraperItem
class DatabloggerSpider(CrawlSpider):
# The name of the spider
name = "datablogger"
# The domains that are allowed (links to other domains are skipped)
allowed_domains = ['http://1.1.1.1:1234/']
# The URLs to start with
start_urls = ['http://1.1.1.1:1234/TestSuites']
# This spider has one rule: extract all (unique and canonicalized) links, follow them and parse them using the parse_items method
rules = [
Rule(
LinkExtractor(
canonicalize=True,
unique=True
),
follow=True,
callback="parse_items"
)
]
# Method which starts the requests by visiting all URLs specified in start_urls
def start_requests(self):
for url in self.start_urls:
yield scrapy.Request(url, callback=self.parse, dont_filter=True)
# Method for parsing items
def parse_items(self, response):
# The list of items that are found on the particular page
items = []
# Only extract canonicalized and unique links (with respect to the current page)
links = LinkExtractor(canonicalize=True, unique=True).extract_links(response)
# Now go through all the found links
item = DatabloggerScraperItem()
item['url_from'] = response.url
for link in links:
item['url_to'] = link.url
items.append(item)
# Return all the found items
return items

Scrapy - remove duplicates and output data as a single list?

I am using the below code to crawl through multiple links on a page and grab a list of data from each corresponding link:
import scrapy
class testSpider(scrapy.Spider):
name = "quotes"
start_urls = ['http://www.website.com']
def parse(self, response):
urls = response.css('div.subject_wrapper > a::attr(href)').extract()
for url in urls:
url = response.urljoin(url)
yield scrapy.Request(url=url, callback=self.getData)
def getData(self, response):
data = {'data': response.css('strong.data::text').extract()}
yield data
It works fine, but as it's returning a list of data for each link, when I output to CSV it looks like the following:
"dalegribel,Chad,Ninoovcov,dalegribel,Gotenks,sillydog22"
"kaylachic,jmargerum,kaylachic"
"Kempodancer,doctordbrew,Gotenks,dalegribel"
"Gotenks,dalegribel,jmargerum"
...
Is there any simple/efficient way of outputting the data as a single list of rows without any duplicates (the same data can appear on multiple pages), similar to the following?
dalegribel
Chad
Ninoovcov
Gotenks
...
I have tried using an array then looping over each element to get an output, but get an error saying yield only supports 'Request, BaseItem, dict or None'. Also, as I would be running this over approx 10k entries, i'm not sure if storing the data in an array would slow the scrape down too much. Thanks.

Not sure if it can be somehow done using Scrapy built-in methods, but the python way would be to create a set of unique elements, check for duplicates, and yeild only unique elements:
class testSpider(scrapy.Spider):
name = "quotes"
start_urls = ['http://www.website.com']
unique_data = set()
def parse(self, response):
urls = response.css('div.subject_wrapper > a::attr(href)').extract()
for url in urls:
url = response.urljoin(url)
yield scrapy.Request(url=url, callback=self.getData)
def getData(self, response):
data_list = response.css('strong.data::text').extract()
for elem in data_list:
if elem and (elem not in self.unique_data):
self.unique_data.add(elem)
yield {'data': elem}

In Scrapy, how do I pass the urls generated in one class to the next class in the script?

The following is my spider's code:
import scrapy
class ProductMainPageSpider(scrapy.Spider):
name = 'ProductMainPageSpider'
start_urls = ['http://domain.com/main-product-page']
def parse(self, response):
for product in response.css('article.isotopeItem'):
yield {
'title': product.css('h3 a::text').extract_first().encode("utf-8"),
'category': product.css('h6 a::text').extract_first(),
'img': product.css('figure a img::attr("src")').extract_first(),
'url': product.css('h3 a::attr("href")').extract_first()
}
class ProductSecondaryPageSpider(scrapy.Spider):
name = 'ProductSecondaryPageSpider'
start_urls = """ URLS IN product['url'] FROM PREVIOUS CLASS """
def parse(self, response):
for product in response.css('article.isotopeItem'):
yield {
'title': product.css('h3 a::text').extract_first().encode("utf-8"),
'thumbnail': product.css('figure a img::attr("src")').extract_first(),
'short_description': product.css('div.summary').extract_first(),
'description': product.css('div.description').extract_first(),
'gallery_images': product.css('figure a img.gallery-item ::attr("src")').extract_first()
}
The first class/part works correctly if I remove the second class/part. It generates my json file correctly with the items requested in it. However, the website I need to crawl is a two-parter. It has a product archive page that shows a products as a thumbnail, title, and category (and this info is not in the next page). Then if you click on one of the thumbnails or titles you get sent to a single product page where there is specific info on the product.
There are a lot of products so I would like to pipe (yield?) the urls in product['url'] to the second class as the "start_urls" list. But I simply don't know how to do that. My knowledge doesn't go far enough to even know what I'm missing or what is going wrong so that I can find a solution.
Check out on line 20 what I want to do.

You don't have to create two spiders for this - you can simply go to the next url and carry over your item i.e.:
def parse(self, response):
item = MyItem()
item['name'] = response.xpath("//name/text()").extract()
next_page_url = response.xpath("//a[#class='next']/#href").extract_first()
yield Request(next_page_url,
self.parse_next,
meta={'item': item} # carry over our item
)
def parse_next(self, response):
# get our carried item from response meta
item = response.meta['item']
item['description'] = response.xpath("//description/text()").extract()
yield item
However if for some reason you realy want to split logic of these two steps you can simply save the results in a file (a json for example: scrapy crawl first_spider -o results.json) and open/iterate through it in your second spider in start_requests() class method which would yield urls, i.e.:
import json
from scrapy import spider
class MySecondSpider(spider):
def start_requests(self):
# this overrides `start_urls` logic
with open('results.json', 'r') as f:
data = json.loads(f.read())
for item in data:
yield Request(item['url'])

Scrapy merge subsite-item with site-item

Im trying to scrape details from a subsite and merge with the details scraped with site. I've been researching through stackoverflow, as well as documentation. However, I still cant get my code to work. It seems that my function to extract additional details from the subsite does not work. If anyone could take a look I would be very grateful.
# -*- coding: utf-8 -*-
from scrapy.spiders import Spider
from scrapy.selector import Selector
from scrapeInfo.items import infoItem
import pyodbc
class scrapeInfo(Spider):
name = "info"
allowed_domains = ["http://www.nevermind.com"]
start_urls = []
def start_requests(self):
#Get infoID and Type from database
self.conn = pyodbc.connect('DRIVER={SQL Server};SERVER=server;DATABASE=dbname;UID=user;PWD=password')
self.cursor = self.conn.cursor()
self.cursor.execute("SELECT InfoID, category FROM dbo.StageItem")
rows = self.cursor.fetchall()
for row in rows:
url = 'http://www.nevermind.com/info/'
InfoID = row[0]
category = row[1]
yield self.make_requests_from_url(url+InfoID, InfoID, category, self.parse)
def make_requests_from_url(self, url, InfoID, category, callback):
request = Request(url, callback)
request.meta['InfoID'] = InfoID
request.meta['category'] = category
return request
def parse(self, response):
hxs = Selector(response)
infodata = hxs.xpath('div[2]/div[2]') # input item path
itemPool = []
InfoID = response.meta['InfoID']
category = response.meta['category']
for info in infodata:
item = infoItem()
item_cur, item_hist = InfoItemSubSite()
# Stem Details
item['id'] = InfoID
item['field'] = info.xpath('tr[1]/td[2]/p/b/text()').extract()
item['field2'] = info.xpath('tr[2]/td[2]/p/b/text()').extract()
item['field3'] = info.xpath('tr[3]/td[2]/p/b/text()').extract()
item_cur['field4'] = info.xpath('tr[4]/td[2]/p/b/text()').extract()
item_cur['field5'] = info.xpath('tr[5]/td[2]/p/b/text()').extract()
item_cur['field6'] = info.xpath('tr[6]/td[2]/p/b/#href').extract()
# Extract additional information about item_cur from refering site
# This part does not work
if item_cur['field6'] = info.xpath('tr[6]/td[2]/p/b/#href').extract():
url = 'http://www.nevermind.com/info/sub/' + item_cur['field6'] = info.xpath('tr[6]/td[2]/p/b/#href').extract()[0]
request = Request(url, housingtype, self.parse_item_sub)
request.meta['category'] = category
yield self.parse_item_sub(url, category)
item_his['field5'] = info.xpath('tr[5]/td[2]/p/b/text()').extract()
item_his['field6'] = info.xpath('tr[6]/td[2]/p/b/text()').extract()
item_his['field7'] = info.xpath('tr[7]/td[2]/p/b/#href').extract()
item['subsite_dic'] = [dict(item_cur), dict(item_his)]
itemPool.append(item)
yield item
pass
# Function to extract additional info from the subsite, and return it to the original item.
def parse_item_sub(self, response, category):
hxs = Selector(response)
subsite = hxs.xpath('div/div[2]') # input base path
category = response.meta['category']
for i in subsite:
item = InfoItemSubSite()
if (category == 'first'):
item['subsite_field1'] = i.xpath('/td[2]/span/#title').extract()
item['subsite_field2'] = i.xpath('/tr[4]/td[2]/text()').extract()
item['subsite_field3'] = i.xpath('/div[5]/a[1]/#href').extract()
else:
item['subsite_field1'] = i.xpath('/tr[10]/td[3]/span/#title').extract()
item['subsite_field2'] = i.xpath('/tr[4]/td[1]/text()').extract()
item['subsite_field3'] = i.xpath('/div[7]/a[1]/#href').extract()
return item
pass
I've been looking at these examples together with a lot of other examples (stackoverflow is great for that!), as well as scrapy documentation, but still unable to understand how I get details send from one function and merged with the scraped items from the original function.
how do i merge results from target page to current page in scrapy?
How can i use multiple requests and pass items in between them in scrapy python

What you are looking here is called request chaining. Your problem is - yield one item from several requests. A solution to this is to chain requests while carrying your item in requests meta attribute.
Example:
def parse(self, response):
item = MyItem()
item['name'] = response.xpath("//div[#id='name']/text()").extract()
more_page = # some page that offers more details
# go to more page and take your item with you.
yield Request(more_page,
self.parse_more,
meta={'item':item})
def parse_more(self, response):
# get your item from the meta
item = response.meta['item']
# fill it in with more data and yield!
item['last_name'] = response.xpath("//div[#id='lastname']/text()").extract()
yield item