My Hacker News spider outputs all the results on one line, instead of one each line, as it can be seen here.
All on the same line
Here is my code.
import scrapy
import string
import urlparse
from scrapy.selector import Selector
from scrapy.selector import HtmlXPathSelector
from scrapy.contrib.linkextractors import LinkExtractor
class HnItem(scrapy.Item):
title = scrapy.Field()
link = scrapy.Field()
score = scrapy.Field()
class HnSpider(scrapy.Spider):
name = 'hackernews'
allowed_domains = ["news.ycombinator.com"]
start_urls = ["https://news.ycombinator.com/"]
def parse(self, response):
sel = response
selector_list = response.xpath('.//table[#class="itemlist"]')
for sel in selector_list:
item = HnItem()
item['title'] = sel.xpath('.//td[#class="title"]/text()').extract()
item['link'] = sel.xpath('.//tr[#class="athing"]/td[3]/a/#href').extract()
item['score'] = sel.xpath('.//td[#class="subtext"]/span/text()').extract()
yield item
and my settings.py file
BOT_NAME = 'hnews'
SPIDER_MODULES = ['hnews.spiders']
NEWSPIDER_MODULE = 'hnews.spiders'
USER_AGENT = 'hnews (+http://www.yourdomain.com)'
FEED_URI = '/used/scrapy/hnews/%(name)s/%(time)s.csv'
FEED_FORMAT = 'csv'
I've tried to implement this among many other solutions but no luck so far. I'm still very new at this, so bear with me if possible.
It is happening because your item pipeline is getting all the lists at once. For expample: The item['title'] is getting a list of all the titles at once which is then transferred to the item pipeline and then written to the csv file directly.
The solution is to iterate over the list and yield it to the item pipeline one at a time. Here's a modified code:
import scrapy
from scrapy.selector import Selector
class HnItem(scrapy.Item):
title = scrapy.Field()
link = scrapy.Field()
score = scrapy.Field()
class HnSpider(scrapy.Spider):
name = 'hackernews'
allowed_domains = ["news.ycombinator.com"]
start_urls = ["https://news.ycombinator.com/"]
def parse(self, response):
sel = Selector(response)
item = HnItem()
title_list = sel.xpath('.//td[#class="title"]/a/text()').extract()[:-2]
link_list= sel.xpath('.//tr[#class="athing"]/td[3]/a/#href').extract()
score_list = sel.xpath('.//td[#class="subtext"]/span/text()').extract()
for x in range(0,len(title_list)):
item['title'] = title_list[x]
item['link'] = link_list[x]
item['score'] = score_list[x]
yield item
Related
I am trying to scrape data of # pages. I have already done a scraper which can scrape data from a single # page. But it suddenly finished the work after scraping of the first page
The whole file with parse function and scrapd function - Scraper.py
# -*- coding: utf-8 -*-
import scrapy
import csv
import os
from scrapy.selector import Selector
from scrapy import Request
class Proddduct(scrapy.Item):
price = scrapy.Field()
description = scrapy.Field()
link = scrapy.Field()
content = scrapy.Field()
class LapadaScraperSpider(scrapy.Spider):
name = 'lapada_scraper2'
allowed_domains = ['http://www.lapada.org']
start_urls = ['https://lapada.org/art-and-antiques/?search=antique']
def parse(self, response):
next_page_url = response.xpath("//ul/li[#class='next']//a/#href").get()
for item in self.scrape(response):
yield item
if next_page_url:
print("Found url: {}".format(next_page_url))
yield scrapy.Request(url=next_page_url, callback=self.parse)
def scrape(self, response):
parser = scrapy.Selector(response)
products = parser.xpath("//div[#class='content']")
for product in products:
item = Proddduct()
XPATH_PRODUCT_DESCRIPTION = ".//strong/text()"
XPATH_PRODUCT_PRICE = ".//div[#class='price']/text()"
XPATH_PRODUCT_LINK = ".//a/#href"
raw_product_description = product.xpath(XPATH_PRODUCT_DESCRIPTION).extract()
raw_product_price = product.xpath(XPATH_PRODUCT_PRICE).extract()
raw_product_link = product.xpath(XPATH_PRODUCT_LINK).extract_first()
item['description'] = raw_product_description
item['price'] = raw_product_price
item['link'] = raw_product_link
yield item
def get_information(self, response):
item = response.meta['item']
item['phonenumber'] = "12345"
yield item
How can I scrape all items in all pages?
Thanks
Change allowed_domains = ['http://www.lapada.org'] to allowed_domains = ['lapada.org']
I have scrapy spider and i am using xpath selectors to extract the contents of the page,kindly check where i am going wrong
from scrapy.contrib.loader import ItemLoader
from scrapy.contrib.spiders import CrawlSpider,Rule
from scrapy.selector import HtmlXPathSelector
from medicalproject.items import MedicalprojectItem
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import HtmlXPathSelector
from scrapy import Request
class MySpider(CrawlSpider):
name = "medical"
allowed_domains = ["yananow.org"]
start_urls = ["http://yananow.org/query_stories.php"]
rules = (
Rule(SgmlLinkExtractor(allow=[r'display_story.php\?\id\=\d+']),callback='parse_page',follow=True),
)
def parse_items(self, response):
hxs = HtmlXPathSelector(response)
titles = hxs.xpath('/html/body/div/table/tbody/tr[2]/td/table/tbody/tr/td')
items = []
for title in titles:
item = MedicalprojectItem()
item["patient_name"] = title.xpath("/html/body/div/table/tbody/tr[2]/td/table/tbody/tr/td/img[1]/text()").extract()
item["stories"] = title.xpath("/html/body/div/table/tbody/tr[2]/td/table/tbody/tr/td/div/font/p/text()").extract()
items.append(item)
return(items)
There are a lot of issues with your code so here is a different approach.
I opted against a CrawlSpider to have more control over the scraping process. Especially with grabbing the name from the query page and the story from a detail page.
I tried to simplify the XPath statements by not diving into the (nested) table structures but looking for patterns of content. So if you want to extract a story ... there must be a link to a story.
Here comes the tested code (with comments):
# -*- coding: utf-8 -*-
import scrapy
class MyItem(scrapy.Item):
name = scrapy.Field()
story = scrapy.Field()
class MySpider(scrapy.Spider):
name = 'medical'
allowed_domains = ['yananow.org']
start_urls = ['http://yananow.org/query_stories.php']
def parse(self, response):
rows = response.xpath('//a[contains(#href,"display_story")]')
#loop over all links to stories
for row in rows:
myItem = MyItem() # Create a new item
myItem['name'] = row.xpath('./text()').extract() # assign name from link
story_url = response.urljoin(row.xpath('./#href').extract()[0]) # extract url from link
request = scrapy.Request(url = story_url, callback = self.parse_detail) # create request for detail page with story
request.meta['myItem'] = myItem # pass the item with the request
yield request
def parse_detail(self, response):
myItem = response.meta['myItem'] # extract the item (with the name) from the response
text_raw = response.xpath('//font[#size=3]//text()').extract() # extract the story (text)
myItem['story'] = ' '.join(map(unicode.strip, text_raw)) # clean up the text and assign to item
yield myItem # return the item
I wrote this spider to scrape reviews of apps from google play. I am partially successful in this. I am able to extract the name, date, and review only.
My questions:
How to get all the reviews as I am only getting only 41.
How to get the rating from the <div>?
import scrapy
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.selector import Selector
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from urlparse import urljoin
class CompItem(scrapy.Item):
rating = scrapy.Field()
data = scrapy.Field()
name = scrapy.Field()
date = scrapy.Field()
class criticspider(CrawlSpider):
name = "gaana"
allowed_domains = ["play.google.com"]
start_urls = ["https://play.google.com/store/apps/details?id=com.gaana&hl=en"]
# rules = (
# Rule(
# SgmlLinkExtractor(allow=('search=jabong&page=1/+',)),
# callback="parse_start_url",
# follow=True),
# )
def parse(self, response):
sites = response.xpath('//div[#class="single-review"]')
items = []
for site in sites:
item = CompItem()
item['data'] = site.xpath('.//div[#class="review-body"]/text()').extract()
item['name'] = site.xpath('.//div/div/span[#class="author-name"]/a/text()').extract()[0]
item['date'] = site.xpath('.//span[#class="review-date"]/text()').extract()[0]
item['rating'] = site.xpath('div[#class="review-info-star-rating"]/aria-label/text()').extract()
items.append(item)
return items
you have
item['rating'] = site.xpath('div[#class="review-info-star-rating"]/aria-label/text()').extract()
should it not be something like:
item['rating'] = site.xpath('.//div[#class="review-info-star-rating"]/aria-label/text()').extract()
?? dunno if it will work, but try :)
You can try this one out:
item['rating'] = site.xpath('.//div[#class="tiny-star star-rating-non-editable-container"]/#aria-label').extract()
I just started learning python / Scrapy. I was able to follow tutorials successfully but I am struggling with a 'test' scraping that I want to do on my own.
What I am trying to do now is go on http://jobs.walmart.com/search/finance-jobs and scrape the job listing.
However, I think I may be doing something wrong in the XPath, but I am not sure what.
There is no "id" for that table, so I am using its class.
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
class MySpider(BaseSpider):
name = "walmart"
allowed_domains = ["jobs.walmart.com"]
start_urls = ["http://jobs.walmart.com/search/finance-jobs"]
def parse(self, response):
hxs = HtmlXPathSelector(response)
titles = hxs.select("//table[#class='tableSearchResults']")
items = []
for titles in titles:
item = walmart()
item ["title"] = titles.select("a/text()").extract()
item ["link"] = titles.select("a/#href").extract()
items.append(item)
return items
here is what the page source looks like:
The problem as you said also, is your XPATH. It is always useful to run:
scrapy view http://jobs.walmart.com/search/finance-jobs
Before running your spider, to see how the website look like from scrapy view.
This should work now:
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
class MySpider(BaseSpider):
name = "walmart"
allowed_domains = ["jobs.walmart.com"]
start_urls = ["http://jobs.walmart.com/search/finance-jobs"]
def parse(self, response):
hxs = HtmlXPathSelector(response)
item = walmart()
titles = hxs.select("//table[#class='tableSearchResults']/tr")
items = []
for title in titles:
if title.select("td[#class='td1']/a").extract():
item ["title"] = title.select("td[#class='td1']/a/text()").extract()
item ["link"] = title.select("td[#class='td1']/a/#href").extract()
items.append(item)
return items
So when i try to scrape product review info from epinions.com, if the main review text is too long, it has a "read more" link to another page.
I took an example from "http://www.epinions.com/reviews/samsung-galaxy-note-16-gb-cell-phone/pa_~1" you'll see what i mean if you look at the first review.
I am wondering: is it possible to have a tiny spider in each iteration of the for loop to grab the url and scrape the review out of the new link? I have the following code, but it doesn't work for the tiny "spider".
Here is my code:
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from epinions_test.items import EpinionsTestItem
from scrapy.http import Response, HtmlResponse
class MySpider(BaseSpider):
name = "epinions"
allow_domains = ["epinions.com"]
start_urls = ['http://www.epinions.com/reviews/samsung-galaxy-note-16-gb-cell-phone/pa_~1']
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.select('//div[#class="review_info"]')
items = []
for sites in sites:
item = EpinionsTestItem()
item["title"] = sites.select('h2/a/text()').extract()
item["star"] = sites.select('span/a/span/#title').extract()
item["date"] = sites.select('span/span/span/#title').extract()
item["review"] = sites.select('p/span/text()').extract()
# Everything works fine and i do have those four columns beautifully printed out, until....
url2 = sites.select('p/span/a/#href').extract()
url = str("http://www.epinions.com%s" %str(url2)[3:-2])
# This url is a string. when i print it out, it's like "http://www.epinions.com/review/samsung-galaxy-note-16-gb-cell-phone/content_624031731332", which looks legit.
response2 = HtmlResponse(url)
# I tried in a scrapy shell, it shows that this is a htmlresponse...
hxs2 = HtmlXPathSelector(response2)
fullReview = hxs2.select('//div[#class = "user_review_full"]')
item["url"] = fullReview.select('p/text()').extract()
# The three lines above works in an independent spider, where start_url is changed to the url just generated and everything.
# However, i got nothing from item["url"] in this code.
items.append(item)
return items
Why item["url"] returns nothing?
Thanks!
You should instantiate a new Request in the callback and pass your item in the meta dict:
from scrapy.http import Request
from scrapy.item import Item, Field
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
class EpinionsTestItem(Item):
title = Field()
star = Field()
date = Field()
review = Field()
class MySpider(BaseSpider):
name = "epinions"
allow_domains = ["epinions.com"]
start_urls = ['http://www.epinions.com/reviews/samsung-galaxy-note-16-gb-cell-phone/pa_~1']
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.select('//div[#class="review_info"]')
for sites in sites:
item = EpinionsTestItem()
item["title"] = sites.select('h2/a/text()').extract()
item["star"] = sites.select('span/a/span/#title').extract()
item["date"] = sites.select('span/span/span/#title').extract()
url = sites.select('p/span/a/#href').extract()
url = str("http://www.epinions.com%s" % str(url)[3:-2])
yield Request(url=url, callback=self.parse_url2, meta={'item': item})
def parse_url2(self, response):
hxs = HtmlXPathSelector(response)
item = response.meta['item']
fullReview = hxs.select('//div[#class = "user_review_full"]')
item["review"] = fullReview.select('p/text()').extract()
yield item
Also see documentation.
Hope that helps.