How to handle ajax data with scrapy - python

I'm making a web spider with scrapy and there comes a problem:I tried to get a group of html data.And it contains the id i need to send ajax request.However,when I tried to get the ajax data together with other data I got with the html , it just goes wrong.How could I solve it?Here's my code:
class DoubanSpider(scrapy.Spider):
name = "douban"
allowed_domains = ["movie.douban.com"]
start_urls = ["https://movie.douban.com/review/best"]
def parse(self, response):
for review in response.css(".review-item"):
rev = Review()
rev['reviewer'] = review.css("a[property='v:reviewer']::text").extract_first()
rev['rating'] = review.css("span[property='v:rating']::attr(class)").extract_first()
rev['title'] = review.css(".main-bd>h2>a::text").extract_first()
number = review.css("::attr(id)").extract_first()
f = scrapy.Request(url='https://movie.douban.com/j/review/%s/full' % number,
callback=self.parse_full_passage)
rev['comment'] = f
yield rev
def parse_full_passage(self, response):
r = json.loads(response.body_as_unicode())
html = r['html']
yield html

You need to fully parse your HTML first and next pass it as a meta to the JSON's callback:
yield scrapy.Request(url='https://movie.douban.com/j/review/%s/full' % number,callback=self.parse_full_passage, meta={'rev': rev} )
And next in your JSON's callback:
def parse_full_passage(self, response):
rev = response.meta["rev"]
r = json.loads(response.body_as_unicode())
.....
yield rev

I would try this:
response = scrapy.Request(url='https://movie.douban.com/j/review/%s/full' % number)
jsonresponse = json.loads(response.body_as_unicode())
rev['comment'] = jsonresponse['html']
You might want to extract stuff from the html field if this is what you need. Alternatively work with this url

Related

scrapy accessing inner URLs

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.

Scrapy pagination issues - new to this stuff

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

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

ScraPy spider crawling but not exporting

I have a ScraPy Code that is running in shell, but when I try to export it to csv, it returns an empty file. It exports data when I do not go into a link and try to parse the description, but once I add the extra method of parsing the contents, it fails to work. Here is the code:
class MonsterSpider(CrawlSpider):
name = "monster"
allowed_domains = ["jobs.monster.com"]
base_url = "http://jobs.monster.com/v-technology.aspx?"
start_urls = [
"http://jobs.monster.com/v-technology.aspx"
]
for i in range(1,5):
start_urls.append(base_url + "page=" + str(i))
rules = (Rule(SgmlLinkExtractor(allow=("jobs.monster.com",))
, callback = 'parse_items'),)
def parse_items(self, response):
sel = Selector(response)
sites = sel.xpath('//div[#class="col-xs-12"]')
#items = []
for site in sites.xpath('.//article[#class="js_result_row"]'):
item = MonsterItem()
item['title'] = site.xpath('.//span[#itemprop = "title"]/text()').extract()
item['company'] = site.xpath('.//span[#itemprop = "name"]/text()').extract()
item['city'] = site.xpath('.//span[#itemprop = "addressLocality"]/text()').extract()
item['state'] = site.xpath('.//span[#itemprop = "addressRegion"]/text()').extract()
item['link'] = site.xpath('.//a[#data-m_impr_a_placement_id= "jsr"]/#href').extract()
follow = ''.join(item["link"])
request = Request(follow, callback = self.parse_dir_contents)
request.meta["item"] = item
yield request
#items.append(item)
#return items
def parse_dir_contents(self, response):
item = response.meta["item"]
item['desc'] = site.xpath('.//div[#itemprop = "description"]/text()').extract()
return item
Taking out the parse_dir_contents and uncommenting the empty "lists" list and "append" code was the original code.
Well, as #tayfun suggests you should use response.xpath or define the site variable.
By the way, you do not need to use sel = Selector(response). Responses come with the xpath function, there is no need to cover it into another selector.
However the main problem is that you restrict the domain of the spider. You define allowed_domains = ["jobs.monster.com"] however if you look at the URL to follow of your custom Request you can see that they are something like http://jobview.monster.com/ or http://job-openings.monster.com. In this case your parse_dir_contents is not executed (the domain is not allowed) and your item does not get returned so you won't get any results.
Change allowed_domains = ["jobs.monster.com"] to
allowed_domains = ["monster.com"]
and you will be fine and your app will work and return items.
You have an error in your parse_dir_contents method:
def parse_dir_contents(self, response):
item = response.meta["item"]
item['desc'] = response.xpath('.//div[#itemprop=description"]/text()').extract()
return item
Note the use of response. I don't know where you got site that you are currently using from.
Also, try to provide the error details when you post a question. Writing "it fails to work" doesn't say much.

Combine FormRequest and CrawlSpider

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

Categories

Resources