Combine FormRequest and CrawlSpider - python

I need to apply FormRequest [From here][1]:
#Request = FormRequest.from_response(
# response,
# formname='frmSearch',
# formdata={'classtype': 'of'},
# #callback=self.parse_links,
# dont_filter=True,
#
# )
For link in start_urls and to all pages that I get from the rules in my СrawlSpider.
class QuokaSpider(CrawlSpider):
name = 'quoka'
allowed_domains = ['www.quoka.de']
start_urls = ['http://www.quoka.de/immobilien/bueros-gewerbeflaechen/']
curr_page = 0
rules = (Rule(LinkExtractor(allow=(r'.+'), restrict_xpaths = [u'//li[#class="arr-rgt active"]',]),
follow=True, callback='parse_links'),
)
def _url(self, url):
return 'http://www.quoka.de' + url
def parse_links(self, response):
hxs = Selector(response)
lnks = hxs.xpath('//a[contains(#class, "img-lmtr") and contains(#class, "multi") or contains(#class, "single")]/#href').extract()
filters = hxs.xpath(u'//div[#class="modal-title"]/text()').extract()
for fil in filters:
print "!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"+fil+"!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!"
for url in lnks:
request = Request(self._url(url), callback=self.parse_object)
yield request
def parse_object(self, response):
item = AnbieterItem()
hxs = Selector(response)
item['Beschreibung'] = hxs.xpath(u'//div[#class="text"]/text()').extract()
# item['Kleinanzeigen_App'] = '1'
# item['Preis'] = '1'
return item
If I try to use "start_request" to the filter, the spider does not use pages from the rules.
How can I solve this problem and apply this filter to start url and urls from rules?

I don't know how to combine CrawlSpider Rules with FormRequest but I'd like to suggest that you replace the CrawlSpider with a generic Spider and create the Requests manually.
The Rule in your code does only take care of following the pagination (as far as i can see). To replace that you could use something like in the following code sample:
import scrapy
class TestSpider(scrapy.Spider):
name = 'quoka'
start_urls = ['http://www.quoka.de/immobilien/bueros-gewerbeflaechen']
def parse(self, response):
request = scrapy.FormRequest.from_response(
response,
formname='frmSearch',
formdata={'classtype': 'of'},
callback=self.parse_filtered
)
print request.body
yield request
def parse_filtered(self,response):
resultList = response.xpath('//div[#id="ResultListData"]/ul/li')
for resultRow in resultList:
xpath_Result_Details = './/div[#class="q-col n2"]/a'
# Check if row has details
if resultRow.xpath(xpath_Result_Details):
result_Details = resultRow.xpath(xpath_Result_Details)
# If YES extract details
title = result_Details.xpath('./#title').extract()
href = result_Details.xpath('./#href').extract()[0]
# Code to request detail pages goes here ...
print title, href
# Use this instead of CrawlSpider to follow the pagination links
xpath_NextPage = '//div[#class="rslt-pagination"]//li[#class="arr-rgt active"]/a'
if response.xpath(xpath_NextPage):
nextPage_href = response.xpath(xpath_NextPage + '/#href').extract()[0]
nextPage_url = 'http://www.quoka.de/immobilien/bueros-gewerbeflaechen' + nextPage_href
nextPage_num = response.xpath(xpath_NextPage + '/#data-qng-page').extract()[0]
# request = scrapy.Request(nextPage_url, callback=self.parse_filtered)
# Create request with formdata ...
request = scrapy.FormRequest.from_response(
response,
formname='frmNaviSearch',
formdata={'pageno': nextPage_num},
callback=self.parse_filtered
)
yield request

Related

Scrapy file, only running the initial start_urls instead of running though the whole list

As the title states, I am trying to run my scrapy program, the issue I am running into is that it seems to be only returning the yield from the initial url (https://www.antaira.com/products/10-100Mbps).
I am unsure on where my program is not working, in my code I have also left some commented code on what I have attempted.
import scrapy
from ..items import AntairaItem
class ProductJumperFix(scrapy.Spider): # classes should be TitleCase
name = 'productJumperFix'
allowed_domains = ['antaira.com']
start_urls = [
'https://www.antaira.com/products/10-100Mbps',
'https://www.antaira.com/products/unmanaged-gigabit'
'https://www.antaira.com/products/unmanaged-10-100Mbps-PoE'
'https://www.antaira.com/products/Unmanaged-Gigabit-PoE'
'https://www.antaira.com/products/Unmanaged-10-gigabit'
'https://www.antaira.com/products/Unmanaged-10-gigabit-PoE'
]
#def start_requests(self):
# yield scrappy.Request(start_urls, self.parse)
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').strip()).getall()
overview = product.css('.products .product-overview::text').getall()
main_image = response.urljoin(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
Thank you everyone!
Follow up question, for some reason when I run "scrapy crawl productJumperFix" im not getting any output from the terminal,not sure how to debug since I can't even see the output errors.
Try using the start_requests method:
For example:
import scrapy
from ..items import AntairaItem
class ProductJumperFix(scrapy.Spider):
name = 'productJumperFix'
allowed_domains = ['antaira.com']
def start_requests(self):
urls = [
'https://www.antaira.com/products/10-100Mbps',
'https://www.antaira.com/products/unmanaged-gigabit',
'https://www.antaira.com/products/unmanaged-10-100Mbps-PoE',
'https://www.antaira.com/products/Unmanaged-Gigabit-PoE',
'https://www.antaira.com/products/Unmanaged-10-gigabit',
'https://www.antaira.com/products/Unmanaged-10-gigabit-PoE',
]
for url in urls:
yield scrapy.Request(url, callback=self.parse)
def parse(self, response):
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()
items['product_link'] = response.url
name = product.css('h1.product-name::text').get().strip()
features = product.css(('section.features h3 + ul').strip()).getall()
overview = product.css('.products .product-overview::text').getall()
main_image = response.urljoin(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

What are the best practices for calling an external api?

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

What is the mistake here?

These are my codes but it seems to be correct,but it doesn't work,please help
HEADER_XPATH = ['//h1[#class="story-body__h1"]//text()']
AUTHOR_XPATH = ['//span[#class="byline__name"]//text()']
PUBDATE_XPATH = ['//div/#data-datetime']
WTAGS_XPATH = ['']
CATEGORY_XPATH = ['//span[#rev="news|source""]//text()']
TEXT = ['//div[#property="articleBody"]//p//text()']
INTERLINKS = ['//div[#class="story-body__link"]//p//a/#href']
DATE_FORMAT_STRING = '%Y-%m-%d'
class BBCSpider(Spider):
name = "bbc"
allowed_domains = ["bbc.com"]
sitemap_urls = [
'http://Www.bbc.com/news/sitemap/',
'http://www.bbc.com/news/technology/',
'http://www.bbc.com/news/science_and_environment/']
def parse_page(self, response):
items = []
item = ContentItems()
item['title'] = process_singular_item(self, response, HEADER_XPATH, single=True)
item['resource'] = urlparse(response.url).hostname
item['author'] = process_array_item(self, response, AUTHOR_XPATH, single=False)
item['pubdate'] = process_date_item(self, response, PUBDATE_XPATH, DATE_FORMAT_STRING, single=True)
item['tags'] = process_array_item(self, response, TAGS_XPATH, single=False)
item['category'] = process_array_item(self, response, CATEGORY_XPATH, single=False)
item['article_text'] = process_article_text(self, response, TEXT)
item['external_links'] = process_external_links(self, response, INTERLINKS, single=False)
item['link'] = response.url
items.append(item)
return items
Your spider is just badly structured and because of that it does nothing.
The scrapy.Spider spider requires start_urls class attribute which should contains list of urls that the spider will use to start the crawl, all of these urls will callback to class method parse which means it's required as well.
Your spider has sitemap_urls class attribute and it's not being used anywhere, also your spider has parse_page class method that is never used anywhere either.
So in short your spider should look something like this:
class BBCSpider(Spider):
name = "bbc"
allowed_domains = ["bbc.com"]
start_urls = [
'http://Www.bbc.com/news/sitemap/',
'http://www.bbc.com/news/technology/',
'http://www.bbc.com/news/science_and_environment/']
def parse(self, response):
# This is a page with all of the articles
article_urls = # find article urls in the pages
for url in article_urls:
yield Request(url, self.parse_page)
def parse_page(self, response):
# This is an article page
items = []
item = ContentItems()
# populate item
return item

Scrapy: Looping through search results only returns first item

I'm scraping a site by going through the search page, then looping through all results within. However it only seems to be returning the first result for each page. I also don't think it's hitting the start page's results either.
Secondly, the price is returning as some sort of Unicode (£ symbol) - how can I remove it altogether just leaving the price?
'regular_price': [u'\xa38.59'],
Here is the HTML:
http://pastebin.com/F8Lud0hu
Here's the spider:
import scrapy
import random
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy.selector import Selector
from cdl.items import candleItem
class cdlSpider(CrawlSpider):
name = "cdl"
allowed_domains = ["www.xxxx.co.uk"]
start_urls = ['https://www.xxxx.co.uk/advanced_search_result.php']
rules = [
Rule(LinkExtractor(
allow=['advanced_search_result\.php\?sort=2a&page=\d*']),
callback='parse_listings',
follow=True)
]
def parse_listings(self, response):
sel = Selector(response)
urls = sel.css('a.product_img')
for url in urls:
url = url.xpath('#href').extract()[0]
return scrapy.Request(url,callback=self.parse_item)
def parse_item(self, response):
candle = candleItem()
n = response.css('.prod_info_name h1')
candle['name'] = n.xpath('.//text()').extract()[0]
if response.css('.regular_price'):
candle['regular_price'] = response.css('.regular_price').xpath('.//text()').extract()
else:
candle['was_price'] = response.css('.was_price strong').xpath('.//text()').extract()
candle['now_price'] = response.css('.now_price strong').xpath('.//text()').extract()
candle['referrer'] = response.request.headers.get('Referer', None)
candle['url'] = response.request.url
yield candle
Yes it's returning only the first result because of your parse_listing method (you're returning the first url and you should be yielding it). I would do something like:
def parse_listings(self, response):
for url in response.css('a.product_img::attr(href)').extract():
yield Request(url, callback=self.parse_item)
In that case I would even do something like:
class CdlspiderSpider(CrawlSpider):
name = 'cdlSpider'
allowed_domains = ['www.xxxx.co.uk']
start_urls = ['https://www.xxxx.co.uk/advanced_search_result.php']
rules = [
Rule(LinkExtractor(allow='advanced_search_result\.php\?sort=2a&page=\d*')),
Rule(LinkExtractor(restrict_css='a.product_img'), callback='parse_item')
]
def parse_item(self, response):
...
if response.css('.regular_price'):
candle['regular_price'] = response.css('.regular_price::text').re_first(r'\d+\.?\d*')
else:
candle['was_price'] = response.css('.was_price strong::text').re_first(r'\d+\.?\d*')
candle['now_price'] = response.css('.now_price strong::text').re_first(r'\d+\.?\d*')
...
return candle
To remove the £, just replace it with an empty string like this:
pricewithpound = u'\xa38.59'
price = pricewithpound.replace(u'\xa3', '')
To investigate the scrapy issue, can you please provide the HTML source ?

whats wrong with this scrapy spider? scrapes only last url

In method parse() spider crawls 4 urls and then sends to method parse_dir_contents() to scrape some data but only 4th url is being scraped I don't understand why it is not scraping other 3 urls?
import scrapy
from v_one.items import VOneItem
import json
class linkedin(scrapy.Spider):
name = "linkedin"
allowed_domains = ["linkedin.com"]
start_urls = [
"https://in.linkedin.com/directory/people-s-1-2-4/",
]
def parse(self, response):
for href in response.xpath('//*[#id="seo-dir"]/div/div/div/ul/li/a/#href'):
url = response.urljoin(href.extract())
print "________________"+url
yield scrapy.Request(url, callback=self.parse_dir_contents)
def parse_dir_contents(self, response):
for sel in response.xpath('//*[#id="profile"]'):
url = response.url
print "____________"+url
item = VOneItem()
item['name'] = sel.xpath('//*[#id="name"]/text()').extract()
item['headline'] = sel.xpath('//*[#id="topcard"]/div/div/div/p/span/text()').extract()
item['current'] = sel.xpath('//*[#id="topcard"]/div/div/div/table/tbody/tr/td/ol/li/span/text()').extract()
item['education'] = sel.xpath('//*[#id="topcard"]/div/div/div/table/tbody/tr/td/ol/li/a/text()').extract()
item['link'] = url
yield item
By inspecting the pages I think that there is no need of the for loop in the parse_dir_contents function. Make the function like this:
def parse_dir_contents(self, response):
item = VOneItem()
item['name'] = response.xpath('//*[#id="name"]/text()').extract()
item['headline'] = response.xpath('//*[#id="topcard"]/div/div/div/p/span/text()').extract()
item['current'] = response.xpath('//*[#id="topcard"]/div/div/div/table/tbody/tr/td/ol/li/span/text()').extract()
item['education'] = response.xpath('//*[#id="topcard"]/div/div/div/table/tbody/tr/td/ol/li/a/text()').extract()
item['link'] = response.url
return item
And check if this solves your issue.

Categories

Resources