Develop Reference

Trying to add multiple yields into a single json file using Scrapy

I am trying to figure out if my scrapy tool is correctly hitting the product_link for the request callback - 'yield scrapy.Request(product_link, callback=self.parse_new_item)'
product_link should be 'https://www.antaira.com/products/10-100Mbps/LNX-500A'
but I have not been able to confirm if my program is jumping into the next step created so that I can retrieve the correct yield return. Thank you!
# Import the required libraries
import scrapy
# Import the Item class with fields
# mentioned int he items.py file
from ..items import AntairaItem
# Spider class name
class productJumper(scrapy.Spider):
# Name of the spider
name = 'productJumper'
# The domain to be scraped
allowed_domains = ['antaira.com']
# The URLs to be scraped from the domain
start_urls = ['https://www.antaira.com/products/10-100Mbps']
#target_url = ['https://www.antaira.com/products/10-100Mbps/LNX-500A']
# First Step: Find every div with the class 'product-container' and step into the links
def parse(self, response):
#product_link = response.urljoin(rel_product_link)
# creating items dictionary
items = AntairaItem()
rel_product_link = response.css('div.center767')
for url in rel_product_link:
rel_product_link = response.xpath('//div[#class="product-container"]//a/#href').get(),
product_link = response.urljoin('rel_product_link'),
items['rel_product_link'] = rel_product_link,
items['product_link'] = product_link
#yield items
# 2nd Step: Return a list of the all products-links that will be scrapped
#yield {
# take the first relative product link
# 'rel_product_link' : rel_product_link,
# 'product_link' : product_link,
#}
yield scrapy.Request(product_link, callback=self.parse_new_item)
# Final Step: Run through each product and Yield the results
def parse_new_item(self, response):
for product in response.css('main.products'):
name = product.css(('h1.product-name::text').strip(' \t\n\r')).get()
features = product.css('section.features h3 + ul').getall()
overview = product.css('.products .product-overview::text').getall()
main_image = product.css('div.selectors img::attr(src)').get()
rel_links = product.xpath("//script/#src[contains(., '/app/site/hosting/scriptlet.nl')]").getall()
items['name'] = name,
items['features'] = features,
items['overview'] = overview,
items['main_image'] = main_image,
items['rel_links'] = rel_links,
yield items

You have a couple of issues:
scrapy items are essentially dictionaries and are therefore mutable. You need to create a unique item for each and every yield statement.
your second parse callback is referencing a variable items that it doesn't have access too because it was defined in your first parse callback.
In your urljoin method you are using a string literal instead of a variable for rel_product_link
In the example below I fixed those issues and made some additional notes
import scrapy
from ..items import AntairaItem
class ProductJumper(scrapy.Spider): # classes should be TitleCase
name = 'productJumper'
allowed_domains = ['antaira.com']
start_urls = ['https://www.antaira.com/products/10-100Mbps']
def parse(self, response):
# iterate through each of the relative urls
for url in response.xpath('//div[#class="product-container"]//a/#href').getall():
product_link = response.urljoin(url) # use variable
yield scrapy.Request(product_link, callback=self.parse_new_item)
def parse_new_item(self, response):
for product in response.css('main.products'):
items = AntairaItem() # Unique item for each iteration
items['product_link'] = response.url # get the product link from response
name = product.css(('h1.product-name::text').get().strip()
features = product.css('section.features h3 + ul').getall()
overview = product.css('.products .product-overview::text').getall()
main_image = product.css('div.selectors img::attr(src)').get()
rel_links = product.xpath("//script/#src[contains(., '/app/site/hosting/scriptlet.nl')]").getall()
items['name'] = name,
items['features'] = features,
items['overview'] = overview,
items['main_image'] = main_image,
items['rel_links'] = rel_links,
yield items

Python scrapy returns uncomplete data

I am creating a scraper for web data scraping.
There are 58 pages and each page has 12 products.
The data should be return as 58 x 12 = 696 products title but it return only data of 404 products only. Here is my code
import scrapy
from fundrazr.items import FundrazrItem
from datetime import datetime
import re
class Fundrazr(scrapy.Spider):
name = "my_scraper"
# First Start Url
start_urls = ["https://perfumehut.com.pk/shop/"]
npages = 57
# This mimics getting the pages using the next button.
for i in range(2, npages + 1):
start_urls.append("https://perfumehut.com.pk/shop/page/"+str(i)+"")
def parse(self, response):
for href in response.xpath("//h3[contains(#class, 'product-title')]/a/#href"):
# add the scheme, eg http://
url = "" + href.extract()
yield scrapy.Request(url, callback=self.parse_dir_contents)
def parse_dir_contents(self, response):
item = FundrazrItem()
# Getting Campaign Title
item['campaignTitle'] = response.xpath("//h1[contains(#class, 'entry-title')]/text()").extract()
yield item
Its a woocommerce website and first page is
https://perfumehut.com.pk/shop/
and other pages as pagination
https://perfumehut.com.pk/shop/page/2/
https://perfumehut.com.pk/shop/page/3/
and up to 58.
I want to know what I did wrong by getting npages ?
Regards

import scrapy
from fundrazr.items import FundrazrItem
from datetime import datetime
import re
class Fundrazr(scrapy.Spider):
name = "my_scraper"
# First Start Url
start_urls = ["https://perfumehut.com.pk/shop/"]
def parse(self, response):
data = FundrazrItem()
for item in response.xpath("//div[contains(#class, 'products elements-grid ')]/div[contains(#class, 'product-grid-item product ')]/h3/a"):
data['campaignTitle'] = item.xpath("./text()").extract_first()
yield data
next_page = response.xpath("//ul[#class='page-numbers']/li[last()]/a/#href").extract_first()
if next_page is not None:
yield scrapy.Request(next_page, callback=self.parse)

scrapy crawl a set of links that might contains next pages

I want to:
Extract links for a certain page
For each link, I need some contents for that link, and the contents of 'next pages' of that link.
Then export it as json file(not important as far as I think regarding my problem)
Currently my spider is like this:
class mySpider(scrapy.Spider):
...
def parse(self, response):
for url in someurls:
yield scrapy.Request(url=url, callback=self.parse_next)
def parse_next(self, response):
for selector in someselectors:
yield { 'contents':...,
...}
nextPage = obtainNextPage()
if nextPage:
yield scrapy.Request(url=next_url, callback=self.parse_next)
The problem is for a set of links that the spider processed, the spider could only reach 'next page' for the last link of that set of links, I viewed that through selenium + chromedriver. For example, I have 10 links(from No.1 to No.10), my spider could only get the next pages for the No.10 link. I don't know if the problem occurred was because of some structural problem of my spider. Below is the full code:
import scrapy
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
class BaiduSpider(scrapy.Spider):
name = 'baidu'
allowed_domains = ['baidu.com']
start_urls = ['http://tieba.baidu.com']
main_url = 'http://tieba.baidu.com/f?kw=%E5%B4%94%E6%B0%B8%E5%85%83&ie=utf-8'
username = ""
password = ""
def __init__(self, username=username, password=password):
#options = webdriver.ChromeOptions()
#options.add_argument('headless')
#options.add_argument('window-size=1200x600')
self.driver = webdriver.Chrome()#chrome_options=options)
self.username = username
self.password = password
# checked
def logIn(self):
elem = self.driver.find_element_by_css_selector('#com_userbar > ul > li.u_login > div > a')
elem.click()
wait = WebDriverWait(self.driver,10).until(EC.presence_of_element_located((By.CSS_SELECTOR,'#TANGRAM__PSP_10__footerULoginBtn')))
elem = self.driver.find_element_by_css_selector('#TANGRAM__PSP_10__footerULoginBtn')
elem.click()
elem = self.driver.find_element_by_css_selector('#TANGRAM__PSP_10__userName')
elem.send_keys(self.username)
elem = self.driver.find_element_by_css_selector('#TANGRAM__PSP_10__password')
elem.send_keys(self.password)
self.driver.find_element_by_css_selector('#TANGRAM__PSP_10__submit').click()
# basic checked
def parse(self, response):
self.driver.get(response.url)
self.logIn()
# wait for hand input verify code
time.sleep(15)
self.driver.get('http://tieba.baidu.com/f?kw=%E5%B4%94%E6%B0%B8%E5%85%83&ie=utf-8')
for url in self.driver.find_elements_by_css_selector('a.j_th_tit')[:2]:
#new_url = response.urljoin(url)
new_url = url.get_attribute("href")
yield scrapy.Request(url=new_url, callback=self.parse_next)
# checked
def pageScroll(self, url):
self.driver.get(url)
SCROLL_PAUSE_TIME = 0.5
SCROLL_LENGTH = 1200
page_height = int(self.driver.execute_script("return document.body.scrollHeight"))
scrollPosition = 0
while scrollPosition < page_height:
scrollPosition = scrollPosition + SCROLL_LENGTH
self.driver.execute_script("window.scrollTo(0, " + str(scrollPosition) + ");")
time.sleep(SCROLL_PAUSE_TIME)
time.sleep(1.2)
def parse_next(self, response):
self.log('I visited ' + response.url)
self.pageScroll(response.url)
for sel in self.driver.find_elements_by_css_selector('div.l_post.j_l_post.l_post_bright'):
name = sel.find_element_by_css_selector('.d_name').text
try:
content = sel.find_element_by_css_selector('.j_d_post_content').text
except: content = ''
try: reply = sel.find_element_by_css_selector('ul.j_lzl_m_w').text
except: reply = ''
yield {'name': name, 'content': content, 'reply': reply}
#follow to next page
next_sel = self.driver.find_element_by_link_text("下一页")
next_url_name = next_sel.text
if next_sel and next_url_name == '下一页':
next_url = next_sel.get_attribute('href')
yield scrapy.Request(url=next_url, callback=self.parse_next)
Thanks for your help, and welcome any suggestions referring my code above

In reference to scraping content from one page, store it, and allow the spider to continue the crawl to the scrape and store items on subsequent pages. You should be configuring your items.py file with the item names and pass the items through each scrapy.Request using a meta.
You should check out https://github.com/scrapy/scrapy/issues/1138
To illustrate how this works, it goes something like this...
1. First, we set up the item.py file with the total items to be scraped on every page.
#items.py
import scrapy
class ScrapyProjectItem(scrapy.Item):
page_one_item = scrapy.Field()
page_two_item = scrapy.Field()
page_three_item = scrapy.Field()
Then its importing the items.py item class to you scrapy spider.
from scrapyproject.items import ScrapyProjectItem
The in your scraper, through each page iteration that has content you want, its initializing the items.py class the pass the items using 'meta' to the next request.
#spider.py
def parse(self, response):
# Initializing the item class
item = ScrapyProjectItem()
# Itemizing the... item lol
item['page_one_item'] = response.css("etcetc::").extract() # set desired attribute
# Here we pass the items to the next concurrent request
for url in someurls: # Theres a million ways to skin a cat, dont know your exact use case.
yield scrapy.Request(response.urljoin(url),
callback=self.parse_next, meta={'item': item})
def parse_next(self, response):
# We load the meta from the previous request
item = response.meta['item']
# We itemize
item['page_two_item'] = response.css("etcetc::").extract()
# We pass meta again to next request
for url in someurls:
yield scrapy.Request(response.urljoin(url),
callback=self.parse_again, meta={'item': item})
def parse_again(self, response):
# We load the meta from the previous request
item = response.meta['item']
# We itemize
item['page_three_item'] = response.css("etcetc::").extract()
# We pass meta again to next request
for url in someurls:
yield scrapy.Request(response.urljoin(url),
callback=self.parse_again, meta={'item': item})
# At the end of each iteration of the crawl loop we can yield the result
yield item
As to the problem about crawler only reaching the last link, I would like to have more info instead of guessing what the problem could be. In your "parse_next", you should add a "print(response.url)" to see if the pages are being reached at all? Im sorry if I didnt understand your problem and wasted everyones time lol.
EDIT
I think I understand better you issue ... You have a list of urls, and each urls has its own set of urls yes?
In your code, the "obtainNextPage()" might be the issue? I have in the past when encountering this type of case have had to use some xpath and/or regex magic to properly obtain the next pages. Im not sure what "obtainNextPage" is doing but... have you thought of parsing the content and use selector to find the next page?? For example.
class mySpider(scrapy.Spider):
...
def parse(self, response):
for url in someurls:
yield scrapy.Request(url=url, callback=self.parse_next)
def parse_next(self, response):
for selector in someselectors:
yield { 'contents':...,
...}
#nextPage = obtainNextPage()
next_page = response.xpath('//path/to/nextbutton/orPage'):
if next_page is not None:
yield scrapy.Request(response.urljoin(next_page),
callback=self.parse_next)
You should still add that "print(response.url)" to see if the url thats being requested is being called correctly, might be urljoin issue.

Webcrawler multiple page iteration

I want to make the crawler go to the next page to extract data any help on what to do. I am a little lost on what to do. I tried scrapy but it is kinda complicated and bs4 is more convenient.
import bs4 as bs
import urllib.request
import pandas as pd
import re
source = urllib.request.urlopen('https://messageboards.webmd.com/').read()
soup = bs.BeautifulSoup(source,'lxml')
df = pd.DataFrame(columns = ['link'],data=[url.a.get('href') for url in soup.find_all('div',class_="link")])
lists=[]
for i in range(0,33):
link = (df.link.iloc[i])
source1 = urllib.request.urlopen(link).read()
soup1 = bs.BeautifulSoup(source1,'lxml')
for url1 in soup1.find_all('a',class_="next"):
next_link = soup1.find('a',href = True, text = re.compile("next"))
if next_link:
lists.append(link+url1.get('href'))

So it looks like you're storing hrefs in a list
for url1 in soup1.find_all('a',class_="next"):
next_link = soup1.find('a',href = True, text = re.compile("next"))
if next_link:
lists.append(link+url1.get('href'))
Now you actually have to do something with them. In this case I'm assuming you want to navigate to each href in your list.
for href in lists:
new_page = urllib.request.urlopen(href).read()
And then you can scrape whatever data you want out of new_page

I've got the same problem. Here is my code example for a page I crawled for exercise. I've chained multiple site requests to get detailed information.
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from capterra.items import CapterraItem
class CapterraCatSpider(CrawlSpider):
name = 'capterra_cat'
#allowed_domains = ['http://www.capterra.com/categories']
start_urls = ['http://www.capterra.com/categories']
# rules = (
# Rule(LinkExtractor(allow=r'Items/'), callback='parse_item', follow=True),
# )
def parse(self, response):
#TEMP
for category in response.css('ol.browse-group-list'):
#Debug: only elements of one category
if category.css('a::text').extract_first() == 'Yoga Studio':
i = CapterraItem()
#Get link to detail page
i['cat_name'] = category.css('a::text').extract_first()
#join link to detail page with base url
i['cat_link'] = response.urljoin(category.css('a::attr(href)').extract_first())
cat_link = i['cat_link']
print cat_link
#call request to detail page and pass response to parse_details method with callback method
request = scrapy.Request(cat_link, callback=self.parse_details)
request.meta['item'] = i
yield request
def parse_details(self,response):
#Debug print
print 'DETAILS!'
#read your items from response meta
item = response.meta['item']
#iterate over listings
for detail in response.css('p.listing-description.milli'):
item['profile_link'] = response.urljoin(detail.css('a.spotlight-link::attr(href)').extract_first())
#call request to profile page to get more information for listing
request = scrapy.Request(item['profile_link'], callback=self.parse_profile)
#set your item to rquest metadata
request.meta['item'] = item
yield request
def parse_profile(self,response):
#Debug print
print 'PROFILE'
item = response.meta['item']
item['product_name'] = response.css('h1.beta.no-margin-bottom::text').extract_first()
item['who_uses_software'] = response.css('div.spotlight-target > p.epsilon > i::text').extract_first()
item['vendor_name'] = response.css('h2.spotlight-vendor-name > span::text').extract_first()
return item

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