I separated the spider from the crawler. I need to extract some data from a website using Python Scrapy using different conditions to get results. So I have the functions in first file:
def parse(self, response):
xpath = '//div[#class="proinfor"]//div[#class="prolist_casinforimg"]/a/#href'
urls = response.xpath(xpath).extract()
for url in urls:
url = url.replace("//", "", 1)
yield scrapy.Request(response.urljoin(url),
callback=self.parse_requem)
yield scrapy.Request(response.urljoin(url),
callback=self.parse_obj)
def parse_requem(self, response):
...
yield scrapy.Request(callback=self.parse_item)
def parse_item(self, response):
parser = BaseParser(response)
return parser.construct_item()
def parse_obj(self, response):
parser = BaseParser(response)
return parser.construct()
And the code in the BaseParser class:
def parse_price(self):
Price = response.body
return Price
def parse_ex(self):
exists = self.xpath('//text()').extract_first()
return exists
def construct(self):
item = dict()
item['ex'] = self.parse_ex()
return item
def construct_item(self):
item = dict()
item['price'] = self.parse_price()
return item
As you can see, I'm trying to separate the data retrieval logic, but instead, I'm only getting the execution result from a single function.
How to separate the parsing logic for a spider?
Related
For an assignment I am trying to build a spider which is able to fetch data from the "www.kaercher.com" webshop. All the products in the webshop are being called by an AJAX call. In order to load in more products, a button named "show more products", has to be pressed. I managed to fetch the required data from the corresponding URL which is being called by the AJAX Call.
However, for my assignment, I am suppose to fetch all (all products/pages) of a certain product. I've been digging around but I can't find a solution. I suppose I am suppose to do something with "isTruncated = true", true indicates that more products can be loaded, false means that there are no more products. (FIXED)
When I manage to fetch the data from all the pages, I need to find a way to fetch all the data from a list of products (create a .csv file with multiple kaercher products, each product has a unique ID which can be seen in the URL, in this case the ID 20035386 is for the high pressure washer). (FIXED)
Links:
Webshop: https://www.kaercher.com/nl/webshop/hogedrukreinigers-resultaten.html
High pressure washer: https://www.kaercher.com/nl/webshop/hogedrukreinigers-resultaten.html
API Url (page1): https://www.kaercher.com/api/v1/products/search/shoppableproducts/partial/20035386?page=1&size=8&isocode=nl-NL
OLD CODE
Spider file
import scrapy
from krc.items import KrcItem
import json
class KRCSpider(scrapy.Spider):
name = "krc_spider"
allowed_domains = ["kaercher.com"]
start_urls = ['https://www.kaercher.com/api/v1/products/search/shoppableproducts/partial/20035386?page=1&size=8&isocode=nl-NL']
def parse(self, response):
item = KrcItem()
data = json.loads(response.text)
for company in data.get('products', []):
item["productid"] = company["id"]
item["name"] = company["name"]
item["description"] = company["description"]
item["price"] = company["priceFormatted"]
yield item
Items file
import scrapy
class KrcItem(scrapy.Item):
productid=scrapy.Field()
name=scrapy.Field()
description=scrapy.Field()
price=scrapy.Field()
pass
NEW CODE
EDIT: 15/08/2019
Thanks to #gangabass I managed to fetch data from all of the product pages. I also manages to fetch the data from different products which are listed in a keyword.csv file. This enables me to fetch data from a list of products. See below for the new code:
Spider file (.py)
import scrapy
from krc.items import KrcItem
import json
import os
import csv
class KRCSpider(scrapy.Spider):
name = "krc_spider"
allowed_domains = ["kaercher.com"]
start_urls = ['https://www.kaercher.com/api/v1/products/search/shoppableproducts/partial/20035386?page=1&size=8&isocode=nl-NL']
def start_requests(self):
"""Read keywords from keywords file amd construct the search URL"""
with open(os.path.join(os.path.dirname(__file__), "../resources/keywords.csv")) as search_keywords:
for keyword in csv.DictReader(search_keywords):
search_text=keyword["keyword"]
url="https://www.kaercher.com/api/v1/products/search/shoppableproducts/partial/{0}?page=1&size=8&isocode=nl-NL".format(
search_text)
# The meta is used to send our search text into the parser as metadata
yield scrapy.Request(url, callback = self.parse, meta = {"search_text": search_text})
def parse(self, response):
current_page = response.meta.get("page", 1)
next_page = current_page + 1
item = KrcItem()
data = json.loads(response.text)
for company in data.get('products', []):
item["productid"] = company["id"]
item["name"] = company["name"]
item["description"] = company["description"]
item["price"] = company["priceFormatted"].replace("\u20ac","").strip()
yield item
if data["isTruncated"]:
yield scrapy.Request(
url="https://www.kaercher.com/api/v1/products/search/shoppableproducts/partial/20035386?page={page}&size=8&isocode=nl-NL".format(page=next_page),
callback=self.parse,
meta={'page': next_page},
)
Items file (.py)
import scrapy
class KrcItem(scrapy.Item):
productid=scrapy.Field()
name=scrapy.Field()
description=scrapy.Field()
price=scrapy.Field()
producttype=scrapy.Field()
pass
keywords file (.csv)
keyword,keywordtype
20035386,Hogedrukreiniger
20072956,Floor Cleaner
You can use response.meta to send current page number between requests:
def parse(self, response):
current_page = response.meta.get("page", 1)
next_page = current_page + 1
item = KrcItem()
data = json.loads(response.text)
for company in data.get('products', []):
item["productid"] = company["id"]
item["name"] = company["name"]
item["description"] = company["description"]
item["price"] = company["priceFormatted"]
yield item
if data["isTruncated"]:
yield scrapy.Request(
url="https://www.kaercher.com/api/v1/products/search/shoppableproducts/partial/20035386?page={page}&size=8&isocode=nl-NL".format(page=next_page),
callback=self.parse,
meta={'page': next_page},
)
I have a url in start_urls array as below:
start_urls = [
'https://www.ebay.com/sch/tp_peacesports/m.html?_nkw=&_armrs=1&_ipg=&_from='
]
def parse(self, response):
shop_title = self.getShopTitle(response)
sell_count = self.getSellCount(response)
self.shopParser(response, shop_title, sell_count)
def shopParser(self, response, shop_title, sell_count):
items = EbayItem()
items['shop_title'] = shop_title
items['sell_count'] = sell_count
if sell_count > 0:
item_links = response.xpath('//ul[#id="ListViewInner"]/li/h3/a/#href').extract()
for link in item_links:
items['item_price'] = response.xpath('//span[#itemprop="price"]/text()').extract_first()
yield items
now in shopParser() inside for loop I have different link and I need to have different response than the original response from start_urls, how I can achive that ?
You need to call requests to new pages, otherwise you will not get any new html. Try something like:
def parse(self, response):
shop_title = response.meta.get('shop_title', self.getShopTitle(response))
sell_count = response.meta.get('sell_count', self.getSellCount(response))
# here you logic with item parsing
if sell_count > 0:
item_links = response.xpath('//ul[#id="ListViewInner"]/li/h3/a/#href').extract()
# yield requests to next pages
for link in item_links:
yield scrapy.Request(response.urljoin(link), meta={'shop_title': shop_title, 'sell_count': sell_count})
These new requests will also be parsed by parse function. Or you can set another callback, if needed.
So let's say I want to write a spider that using the Facebook API to calculate the likes on every page of a website. If I import the requests library, I'm able to call the Facebook graph API as follows.
import scrapy
import json
import requests
API_KEY="KEY_GOES_HERE"
class WebSite(scrapy.Spider):
name = "website_page"
allowed_domains = ["website.com"]
start_urls = ['https://website.com/']
def get_likes(self,url):
base='https://graph.facebook.com/{}?access_token={}'.format(url,API_KEY)
data=requests.get(base)
return self.parse_likes(data)
def parse_likes(self, data):
data = json.loads(data.text)
return data['id'],data['share']['comment_count'],data['share']['share_count']
def parse(self, response):
item= {}
item['url'] = response.url
links = response.css('a::attr(href)').extract()
item['fb_url'],item['shares'],item['comments'] = self.get_likes(response.url)
for link in links:
link = response.urljoin(link)
item['link'] = link
yield scrapy.Request(link, callback=self.parse)
yield item
However, I can't seem to get this code to work if, rather than using the requests, I use the scrapy.Request call. Something like this.
import scrapy
import json
import requests
API_KEY="KEY_GOES_HERE"
class WebSite(scrapy.Spider):
name = "website_page"
allowed_domains = ["website.com"]
start_urls = ['https://website.com/']
def get_likes(self,url):
base='https://graph.facebook.com/{}?access_token={}'.format(url,API_KEY)
return scrapy.Request(base,callback=self.parse_likes)
def parse_likes(self, data):
data = json.loads(data.text)
return data['id'],data['share']['comment_count'],data['share']['share_count']
def parse(self, response):
item= {}
links = response.css('a::attr(href)').extract()
item['url'] = response.url
item['fb_data']=self.get_likes(response.url).body
for link in links:
link = response.urljoin(link)
item['link'] = link
yield scrapy.Request(link, callback=self.parse)
yield item
In this case, I just get a blank response for the Facebook data. I think i'm missing some understanding about how the scrapy.Request method works relative to the standard requests library. Any ideas?
This is a very common case: How to yield from item from multiple urls?
And the most common solution is to chain requests by carrying your item in request.meta paramater.
For your example implementation with this logic could look like:
class WebSite(scrapy.Spider):
base='https://graph.facebook.com/{}?access_token={}'.format
api_key = '1234'
def parse(self, response):
links = response.css('a::attr(href)').extract()
for link in links:
item= {}
item['url'] = response.url
item['fb_data']=self.get_likes(response.url).body
item['link'] = response.urljoin(link)
api_url = self.base(self.api_key, link)
yield scrapy.Request(api_url,
callback=self.parse_likes,
meta={'item': item})
def parse_likes(self, response):
item = response.meta['item']
data = json.loads(data.text)
share_count = data['id'],data['share']['comment_count'],data['share']['share_count']
item['share_count'] = share_count
yield item
I am trying to make a scrapy bot that utilizes pagination but having no success...
The bot crawls through all of the links on the first page one but never goes on to the next page. I have read a ton of different threads and I cant figure this out at all. I am very new to web scraping to please feel free to hammer the crap out of my code.
import time
from scrapy.spiders import CrawlSpider, Rule
#from scrapy.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.linkextractors import LinkExtractor
from scrapy.selector import Selector
from scrapy.http.request import Request
from tutorial.items import TutorialItem
#from scrapy_tutorial.items import ScrapyTutorialItem
class raytheonJobsPageSpider(CrawlSpider):
name = "raytheonJobsStart"
allowed_domains = ["jobs.raytheon.com"]
start_urls = [
"https://jobs.raytheon.com/search-jobs"
]
rules = ( Rule(LinkExtractor(restrict_xpaths=('//div[#class="next"]',)), callback='parse_listings',follow=True), )
def parse_start_url(self, response):
'''
Crawl start URLs
'''
return self.parse_listings(response)
def parse_listings(self, response):
'''
Extract data from listing pages
'''
sel = Selector(response)
jobs = response.xpath(
'//*[#id="search-results-list"]/ul/*/a/#href'
).extract()
nextLink = response.xpath('//a[#class="next"]').extract()
print "This is just the next page link - ",nextLink
for job_url in jobs:
job_url = self.__normalise(job_url)
job_url = self.__to_absolute_url(response.url, job_url)
yield Request(job_url, callback=self.parse_details)
def parse_details(self, response):
'''
Extract data from details pages
'''
sel = Selector(response)
job = sel.xpath('//*[#id="content"]')
item = TutorialItem()
# Populate job fields
item['title'] = job.xpath('//*[#id="content"]/section[1]/div/h1/text()').extract()
jobTitle=job.xpath('//*[#id="content"]/section[1]/div/h1/text()').extract()
item['reqid'] = job.xpath('//*[#id="content"]/section[1]/div/span[1]/text()').extract()
item['location'] = job.xpath('//*[#id="content"]/section[1]/div/span[last()]/text()').extract()
item['applink'] = job.xpath('//*[#id="content"]/section[1]/div/a[2]/#href').extract()
item['description'] = job.xpath('//*[#id="content"]/section[1]/div/div').extract()
item['clearance'] = job.xpath('//*[#id="content"]/section[1]/div/*/text()').extract()
#item['page_url'] = response.url
item = self.__normalise_item(item, response.url)
time.sleep(1)
return item
def __normalise_item(self, item, base_url):
'''
Standardise and format item fields
'''
# Loop item fields to sanitise data and standardise data types
for key, value in vars(item).values()[0].iteritems():
item[key] = self.__normalise(item[key])
# Convert job URL from relative to absolute URL
#item['job_url'] = self.__to_absolute_url(base_url, item['job_url'])
return item
def __normalise(self, value):
print self,value
# Convert list to string
value = value if type(value) is not list else ' '.join(value)
# Trim leading and trailing special characters (Whitespaces, newlines, spaces, tabs, carriage returns)
value = value.strip()
return value
def __to_absolute_url(self, base_url, link):
'''
Convert relative URL to absolute URL
'''
import urlparse
link = urlparse.urljoin(base_url, link)
return link
def __to_int(self, value):
'''
Convert value to integer type
'''
try:
value = int(value)
except ValueError:
value = 0
return value
def __to_float(self, value):
'''
Convert value to float type
'''
try:
value = float(value)
except ValueError:
value = 0.0
return value
You dont need PhantomJS or Splash.
By inspecting the AJAX calls I found that they are loading jobs via AJAX calls to this URL
You can see CurrentPage parameter at the end of URL.
And the result is returned in JSON format, and all jobs are on the key named results
I created a project on my side and I created fully 100% working code for you. Here is link to that in github, just download and run it ... you dont have to do anything at all :P
Download whole working project fomr here https://github.com/mani619cash/raytheon_pagination
Basic logic is here
class RaytheonspiderSpider(CrawlSpider):
name = "raytheonJobsStart"
page = 180
ajaxURL = "https://jobs.raytheon.com/search-jobs/results?ActiveFacetID=0&RecordsPerPage=15&Distance=50&RadiusUnitType=0&Keywords=&Location=&Latitude=&Longitude=&ShowRadius=False&CustomFacetName=&FacetTerm=&FacetType=0&SearchResultsModuleName=Search+Results&SearchFiltersModuleName=Search+Filters&SortCriteria=5&SortDirection=1&SearchType=5&CategoryFacetTerm=&CategoryFacetType=&LocationFacetTerm=&LocationFacetType=&KeywordType=&LocationType=&LocationPath=&OrganizationIds=&CurrentPage="
def start_requests(self):
yield Request(self.ajaxURL + str(self.page), callback=self.parse_listings)
def parse_listings(self, response):
resp = json.loads(response.body)
response = Selector(text = resp['results'])
jobs = response.xpath('//*[#id="search-results-list"]/ul/*/a/#href').extract()
if jobs:
for job_url in jobs:
job_url = "https://jobs.raytheon.com" + self.__normalise(job_url)
#job_url = self.__to_absolute_url(response.url, job_url)
yield Request(url=job_url, callback=self.parse_details)
else:
raise CloseSpider("No more pages... exiting...")
# go to next page...
self.page = self.page + 1
yield Request(self.ajaxURL + str(self.page), callback=self.parse_listings)
Change
restrict_xpaths=('//div[#class="next"]',)) to
restrict_xpaths=('//a[#class="next"]',))
If this not working then do a recursive call to parse_listings function
def parse_listings(self, response):
'''
Extract data from listing pages
'''
sel = Selector(response)
jobs = response.xpath(
'//*[#id="search-results-list"]/ul/*/a/#href'
).extract()
nextLink = response.xpath('//a[#class="next"]').extract()
print "This is just the next page link - ",nextLink
for job_url in jobs:
job_url = self.__normalise(job_url)
job_url = self.__to_absolute_url(response.url, job_url)
yield Request(job_url, callback=self.parse_details)
yield Request(pagination link here, callback=self.parse_listings)
I am on mobile so cant type code. I hope the logic i told you makes sense
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