Is there a way to tell scrapy to stop crawling based upon condition in the 2nd level page? I am doing the following:
I have a start_url to begin with (1st level page)
I have set of urls extracted from the start_url using parse(self,
response)
Then I add queue the links using Request with callback as parseDetailPage(self, response)
Under parseDetail (2nd level page) I come to know if I can stop crawling or not
Right now I am using CloseSpider() to accomplish this, but the problem is that the urls to be parsed are already queued by the time I start crawling second level pages and I do not know how to remove them from the queue. Is there a way to sequentially crawl the list of links and then be able to stop in parseDetailPage?
global job_in_range
start_urls = []
start_urls.append("http://sfbay.craigslist.org/sof/")
def __init__(self):
self.job_in_range = True
def parse(self, response):
hxs = HtmlXPathSelector(response)
results = hxs.select('//blockquote[#id="toc_rows"]')
items = []
if results:
links = results.select('.//p[#class="row"]/a/#href')
for link in links:
if link is self.end_url:
break;
nextUrl = link.extract()
isValid = WPUtil.validateUrl(nextUrl);
if isValid:
item = WoodPeckerItem()
item['url'] = nextUrl
item = Request(nextUrl, meta={'item':item},callback=self.parseDetailPage)
items.append(item)
else:
self.error.log('Could not parse the document')
return items
def parseDetailPage(self, response):
if self.job_in_range is False:
raise CloseSpider('End date reached - No more crawling for ' + self.name)
hxs = HtmlXPathSelector(response)
print response
body = hxs.select('//article[#id="pagecontainer"]/section[#class="body"]')
item = response.meta['item']
item['postDate'] = body.select('.//section[#class="userbody"]/div[#class="postinginfos"]/p')[1].select('.//date/text()')[0].extract()
if item['jobTitle'] is 'Admin':
self.job_in_range = False
raise CloseSpider('Stop crawling')
item['jobTitle'] = body.select('.//h2[#class="postingtitle"]/text()')[0].extract()
item['description'] = body.select(str('.//section[#class="userbody"]/section[#id="postingbody"]')).extract()
return item
Do you mean that you would like to stop the spider and resume it without parsing the urls which have been parsed?
If so, you may try to set the JOB_DIR setting. This setting can keep the request.queue in specified file on the disk.
Related
I'm trying to make a spider that goes through a certain amount of start urls and if the resulting page is the right one I yield another request. The problem is that if I try anyway of not yielding a second request the spider will stop directly. There are no problems if I yield the second request.
Here is the relevant code:
def start_requests(self):
urls = ['https://www.hltv.org' + player for player in self.hashPlayers]
print(len(urls))
for url in urls:
return [scrapy.Request(url=url, callback=self.parse)]
def parse(self, response):
result = response.xpath("//div[#class = 'playerTeam']//a/#href").get()
if result is None:
result = response.xpath("//span[contains(concat(' ',normalize-space(#class),' '),' profile-player-stat-value bold ')]//a/#href").get()
if result is not None:
yield scrapy.Request(
url = "https://www.hltv.org" + result,
callback = self.parseTeam
)
So I want a way to make the spider to continue after I call the parse function and don't yield a request.
In below code I am trying to collect email ids from a website. It can be on contact or about us page.
From parse method I follow extemail method for all those pages.
From every page I collected few email ids.
Now I need to print them with original record sent to init method.
For example:
record = "https://www.wockenfusscandies.com/"
I want to print output as,
https://www.wockenfusscandies.com/|abc#gamil.com|def#outlook.com
I am not able to store them in self.emails and deliver back to init method.
Please help.
import scrapy
from scrapy.crawler import CrawlerProcess
class EmailSpider(scrapy.Spider):
def __init__(self, record):
self.record = record
self.emails = []
url = record.split("|")[4]
if not url.startswith("http"):
url = "http://{}".format(url)
if url:
self.start_urls = ["https://www.wockenfusscandies.com/"]
else:
self.start_urls = []
def parse(self, response):
contact_list = [a.attrib['href'] for a in response.css('a') if 'contact' in a.attrib['href'] or 'about' in a.attrib['href']]
contact_list.append(response.request.url)
for fllink in contact_list:
yield response.follow(fllink, self.extemail)
def extemail(self, response):
emails = response.css('body').re('[a-zA-Z0-9_.+-]+#[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+')
yield {
'emails': emails
}
process = CrawlerProcess({
'USER_AGENT': 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1)'
})
f = open("/Users/kalpesh/work/data/test.csv")
for rec in f:
process.crawl(EmailSpider, record=rec)
f.close()
process.start()
If I understand your intend correctly you could try the following proceeding:
a) collect the mail-ids in self.emails like
def extemail(self, response):
emails = response.css('body').re('[a-zA-Z0-9_.+-]+#[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+')
self.emails = emails.copy()
yield {
'emails': emails
}
(Or on what other way you get the email-ids from emails)
b) add a close(self, reason) method as in GitHub-Example which is called when the spider has finished
def close(self, reason):
mails_for_record = ""
for mail in self.emails:
mails_for_record += mail + "|"
print(self.record + mails_for_record)
Please also note, I read somewhere that for some versions of Scrapy it is def close(self, reason), for others it is def closed(self, reason).
Hope, this proceeding helps you.
You should visit all the site pages before yielding result for this one site.
This means that you should have queue of pages to visit and results storage.
It can be done using meta.
Some pseudocode:
def parse(self, response):
meta = response.meta
if not meta.get('seen'):
# -- finding urls of contact and about us pages --
# -- putting it to meta['queue'] --
# -- setting meta['seen'] = True
page_emails_found = ...getting emails here...
# --- extending already discovered emails
# --- from other pages/initial empty list with new ones
meta['emails'].extend(page_emails_found)
# if queue isn't empty - yielding new request
if meta['queue']:
next_url = meta['queue'].pop()
yield Request(next_url, callback=self.parse, meta=copy(meta))
# if queue is empty - yielding result from meta
else:
yield {'url': current_domain, 'emails': meta['emails']}
Something like this..
I'm trying to scrape data from amazon India website. I am not able collect response and parse the elements using the yield() method when:
1) I have to move from product page to review page
2) I have to move from one review page to another review page
Product page
Review page
Code flow:
1) customerReviewData() calls the getCustomerRatingsAndComments(response)
2) The getCustomerRatingsAndComments(response)
finds the URL of the review page and call the yield request method with getCrrFromReviewPage(request) as callback method, with url of this review page
3) getCrrFromReviewPage() gets new response of the firstreview page and scrape all the elements from the first review page (page loaded) and add it to customerReviewDataList[]
4) get URL of the next page if it exists and recursively call getCrrFromReviewPage() method, and crawl elements from next page, until all the review page is crawled
5) All the reviews gets added to the customerReviewDataList[]
I have tried playing around with yield() changing the parameters and also looked up the scrapy documentation for yield() and Request/Response yield
# -*- coding: utf-8 -*-
import scrapy
import logging
customerReviewDataList = []
customerReviewData = {}
#Get product name in <H1>
def getProductTitleH1(response):
titleH1 = response.xpath('normalize-space(//*[#id="productTitle"]/text())').extract()
return titleH1
def getCustomerRatingsAndComments(response):
#Fetches the relative url
reviewRelativePageUrl = response.css('#reviews-medley-footer a::attr(href)').extract()[0]
if reviewRelativePageUrl:
#get absolute URL
reviewPageAbsoluteUrl = response.urljoin(reviewRelativePageUrl)
yield Request(url = reviewPageAbsoluteUrl, callback = getCrrFromReviewPage())
self.log("yield request complete")
return len(customerReviewDataList)
def getCrrFromReviewPage():
userReviewsAndRatings = response.xpath('//div[#id="cm_cr-review_list"]/div[#data-hook="review"]')
for userReviewAndRating in userReviewsAndRatings:
customerReviewData[reviewTitle] = response.css('#cm_cr-review_list .review-title span ::text').extract()
customerReviewData[reviewDescription] = response.css('#cm_cr-review_list .review-text span::text').extract()
customerReviewDataList.append(customerReviewData)
reviewNextPageRelativeUrl = response.css('#cm_cr-pagination_bar .a-pagination .a-last a::attr(href)')[0].extract()
if reviewNextPageRelativeUrl:
reviewNextPageAbsoluteUrl = response.urljoin(reviewNextPageRelativeUrl)
yield Request(url = reviewNextPageAbsoluteUrl, callback = getCrrFromReviewPage())
class UsAmazonSpider(scrapy.Spider):
name = 'Test_Crawler'
allowed_domains = ['amazon.in']
start_urls = ['https://www.amazon.in/Philips-Trimmer-Cordless-Corded-QT4011/dp/B00JJIDBIC/ref=sr_1_3?keywords=philips&qid=1554266853&s=gateway&sr=8-3']
def parse(self, response):
titleH1 = getProductTitleH1(response),
customerReviewData = getCustomerRatingsAndComments(response)
yield{
'Title_H1' : titleH1,
'customer_Review_Data' : customerReviewData
}
I'm getting the following response:
{'Title_H1': (['Philips Beard Trimmer Cordless and Corded for Men QT4011/15'],), 'customer_Review_Data': <generator object getCustomerRatingsAndComments at 0x048AC630>}
The "Customer_review_Data" should be a list of dict of title and review
I am not able to figure out as to what mistake I am doing here.
When I use the log() or print() to see what data is captured in customerReviewDataList[], unable to see the data in the console either.
I am able to scrape all the reviews in customerReviewDataList[], if they are present in the product page,
In this scenario where I have to use the yield function I am getting the output stated above like this [https://ibb.co/kq8w6cf]
This is the kind of output I am looking for:
{'customerReviewTitle': ['Difficult to find a charger adapter'],'customerReviewComment': ['I already have a phillips trimmer which was only cordless. ], 'customerReviewTitle': ['Good Product'],'customerReviewComment': ['Solves my need perfectly HK']}]}
Any help is appreciated. Thanks in advance.
You should complete the Scrapy tutorial. The Following links section should be specially helpful to you.
This is a simplified version of your code:
def data_request_iterator():
yield Request('https://example.org')
class MySpider(Spider):
name = 'myspider'
start_urls = ['https://example.com']
def parse(self, response):
yield {
'title': response.css('title::text').get(),
'data': data_request_iterator(),
}
Instead, it should look like this:
class MySpider(Spider):
name = 'myspider'
start_urls = ['https://example.com']
def parse(self, response):
item = {
'title': response.css('title::text').get(),
}
yield Request('https://example.org', meta={'item': item}, callback=self.parse_data)
def parse_data(self, response):
item = response.meta['item']
# TODO: Extend item with data from this second response as needed.
yield item
I have an agenda as a starting page. This page contains the start times and titles of events and links to the detail page of each event.
My spider extracts all events details (description, location, etc) on the detail page of each single event, except the start time i have to extract on my start page.
How can i extract start time from the start page and other data on each detail pages ?
What is the scrappy way to go ? Using meta['item'] ? i don't get it...
This is my spider for now. Any help greatly appreciated!
class LuSpider(scrapy.Spider):
name = "lu"
allowed_domains = ["example.com"]
start_urls = ["http://www.example.com/agenda"]
def parse(self, response):
for href in response.css("div.toggle_container_show > div > a::attr('href')"):
url = response.urljoin(href.extract())
yield scrapy.Request(url, callback=self.parse_agenda_contents)
def parse_agenda_contents(self, response):
for sel in response.xpath('//div[#class="container"]'):
item = LuItem()
item['EventTitle'] = sel.xpath('div[#class="content"]/div/div[#class="sliderContent"]/h1[#id]/text()').extract()
item['Description'] = sel.xpath('div[#class="content"]/div/div[#class="sliderContent"]//p').extract()
yield item
Edit:
I tried to extract start time from the start page using request.meta['item'] and get a list of all the start time in the start page for each event. How to get the start time for each event ?
Can someone show me the right direction ?
class LuSpider(scrapy.Spider):
name = "lu"
allowed_domains = ["example.com"]
start_urls = ["http://www.example.com/agenda"]
def parse(self, response):
item = LuItem()
item['StartTime'] = response.xpath('//div[contains(., "H")]/span/text()').extract()
for href in response.css("div.toggle_container_show > div > a::attr('href')"):
url = response.urljoin(href.extract())
request = scrapy.Request(url, callback=self.parse_agenda_contents)
request.meta['item'] = item
yield request
def parse_agenda_contents(self, response):
for sel in response.xpath('//div[#class="container"]'):
item = response.meta['item']
item['EventTitle'] = sel.xpath('div[#class="content"]/div/div[#class="sliderContent"]/h1[#id]/text()').extract()
item['Description'] = sel.xpath('div[#class="content"]/div/div[#class="sliderContent"]//p').extract()
yield item
You are right. Using meta would do it in your case. Please see the official documentation here: http://doc.scrapy.org/en/latest/topics/request-response.html#passing-additional-data-to-callback-functions
def parse_page1(self, response):
item = MyItem()
item['main_url'] = response.url
request = scrapy.Request("http://www.example.com/some_page.html",
callback=self.parse_page2)
request.meta['item'] = item
return request
def parse_page2(self, response):
item = response.meta['item']
item['other_url'] = response.url
return item
This worked :
class LuSpider(scrapy.Spider):
name = "lu"
allowed_domains = ["example.com"]
start_urls = ["http://www.example.com/agenda"]
def parse(self, response):
StartTimes = response.xpath('//div[#class="toggle_container_show"]/div/span/text()').extract()
urls =response.xpath('//div[#class="toggle_container_show"]/div/a/#href').extract()
for StartTime,url in zip(StartTimes,urls):
item = LuItem()
item['StartTime'] = StartTime
request = Request(url,callback = self.parse_agenda_contents)
request.meta['item'] = item
yield request
def parse_agenda_contents(self, response):
for sel in response.xpath('//div[#class="container"]'):
item = response.meta['item']
item['EventTitle'] = sel.xpath('div[#class="content"]/div/div[#class="sliderContent"]/h1[#id]/text()').extract()
item['Description'] = sel.xpath('div[#class="content"]/div/div[#class="sliderContent"]//p').extract()
yield item
In my spider after receiving response I want to download and show captcha image and then continue crawling:
def get_captcha(self, response):
print '\nLoading captcha...\n'
item = CaptchaItem()
hxs = HtmlXPathSelector(response)
captcha_img_src = hxs.select('//*[#id="captcha-image"]/#src').extract()[0]
item['image_urls'] = [captcha_img_src]
return item
But I don't know when image is loaded and how to continue crawling after that.
FYI: Captcha image can't be downloaded without cookies.
Thanks in advance!
Use yield instead of return:
def get_captcha(self, response):
print '\nLoading captcha...\n'
item = CaptchaItem()
hxs = HtmlXPathSelector(response)
captcha_img_src = hxs.select('//*[#id="captcha-image"]/#src').extract()[0]
item['image_urls'] = [captcha_img_src]
yield item
#you may display here your scraped item and after that
#your further post request goes here...
yield your_request