here's my code. Actually I followed the example in "Recursively Scraping Web Pages With Scrapy" and it seems I have included a mistake somewhere.
Can someone help me find it, please? It's driving me crazy, I only want all the results from all the result pages. Instead it gives me the results from page 1.
Here's my code:
import scrapy
from scrapy.selector import Selector
from scrapy.spiders import CrawlSpider, Rule
from scrapy.http.request import Request
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from githubScrape.items import GithubscrapeItem
class GithubSpider(CrawlSpider):
name = "github2"
allowed_domains = ["github.com"]
rules = (
Rule(SgmlLinkExtractor(allow=(), restrict_xpaths=('//*[contains(#class, "next_page")]')), callback='parse_items', follow=True),
)
def start_requests(self):
baseURL = 'https://github.com/search?utf8=%E2%9C%93&q=eagle+SYSTEM+extension%3Asch+size%3A'
for i in range(10000, 20000, +5000):
url = baseURL+str(i+1)+".."+str(i+5000)+'&type=Code&ref=searchresults'
print "URL:",url
yield Request(url, callback=self.parse_items)
def parse_items(self, response):
hxs = Selector(response)
resultParagraphs = hxs.xpath('//div[contains(#id,"code_search_results")]//p[contains(#class, "title")]')
items = []
for p in resultParagraphs:
hrefs = p.xpath('a/#href').extract()
projectURL = hrefs[0]
schemeURL = hrefs[1]
lastIndexedOn = p.xpath('.//span/time/#datetime').extract()
i = GithubscrapeItem()
i['counter'] = self.count
i['projectURL'] = projectURL
i['schemeURL'] = schemeURL
i['lastIndexedOn'] = lastIndexedOn
items.append(i)
return(items)
I didn't find your code on the link you passed, but I think the problem is that you are never using the rules.
Scrapy starts crawling by calling the start_requests method, but the rules are compiled and used on the parse method, which you are not using because your requests go directly from start_requests to parse_items.
You could remove the callback on the start_requests method if you want the rules to be applied on that level.
Related
I am trying to build this crawler to get housing data from craigslist,
but the crawler stops after fetching the first page and does not go to the next page .
Here is the code , it works for the first page ,but for the love of god I dont understand why it does not get to the next page .Any insight is really appreciated .I followed this part from scrapy tutorial
import scrapy
import re
from scrapy.linkextractors import LinkExtractor
class QuotesSpider(scrapy.Spider):
name = "craigslistmm"
start_urls = [
"https://vancouver.craigslist.ca/search/hhh"
]
def parse_second(self,response):
#need all the info in a dict
meta_dict = response.meta
for q in response.css("section.page-container"):
meta_dict["post_details"]= {
"location":
{"longitude":q.css("div.mapAndAttrs div.mapbox div.viewposting::attr(data-longitude)" ).extract(),
"latitude":q.css("div.mapAndAttrs div.mapbox div.viewposting::attr(data-latitude)" ).extract()},
"detailed_info": ' '.join(q.css('section#postingbody::text').extract()).strip()
}
return meta_dict
def parse(self, response):
pattern = re.compile("\/([a-z]+)\/([a-z]+)\/.+")
for q in response.css("li.result-row"):
post_urls = q.css("p.result-info a::attr(href)").extract_first()
mm = re.match(pattern, post_urls)
neighborhood= q.css("p.result-info span.result-meta span.result-hood::text").extract_first()
next_url = "https://vancouver.craigslist.ca/"+ post_urls
request = scrapy.Request(next_url,callback=self.parse_second)
#next_page = response.xpath('.//a[#class="button next"]/#href').extract_first()
#follow_url = "https://vancouver.craigslist.ca/" + next_page
#request1 = scrapy.Request(follow_url,callback=self.parse)
#yield response.follow(next_page,callback = self.parse)
request.meta['id'] = q.css("li.result-row::attr(data-pid)").extract_first()
request.meta['pricevaluation'] = q.css("p.result-info span.result-meta span.result-price::text").extract_first()
request.meta["information"] = q.css("p.result-info span.result-meta span.housing::text" ).extract_first()
request.meta["neighborhood"] =q.css("p.result-info span.result-meta span.result-hood::text").extract_first()
request.meta["area"] = mm.group(1)
request.meta["adtype"] = mm.group(2)
yield request
#yield scrapy.Request(follow_url, callback=self.parse)
next_page = LinkExtractor(allow="s=\d+").extract_links(response)[0]
# = "https://vancouver.craigslist.ca/" + next_page
yield response.follow(next_page.url,callback=self.parse)
The problem seems to be with the next_page extraction using LinkExtractor. If you look in the look, you'll see duplicate requests being filtered. There are more links on the page that satisfy your extraction rule and maybe they are not extracted in any particular order (or not in the order you wish).
I think better approach is to extract exactly the information you want, try it with this:
next_page = response.xpath('//span[#class="buttons"]//a[contains(., "next")]/#href').extract_first()
As seems to frequently happen here, I am quite new to Python 2.7 and Scrapy. Our project has us scraping website date, following some links and more scraping, and so on. This was all working fine. Then I updated Scrapy.
Now when I launch my spider, I get the following message:
This wasn't coming up anywhere previously (none of my prior error messages looked anything like this). I am now running scrapy 1.1.0 on Python 2.7. And none of the spiders that had previously worked on this project are working.
I can provide some example code if need be, but my (admittedly limited) knowledge of Python suggests to me that its not even getting to my script before bombing out.
EDIT:
OK, so this code is supposed to start at the first authors page for Deakin University academics on The Conversation, and go through and scrape how many articles they have written and comments they have made.
import scrapy
from ltuconver.items import ConversationItem
from ltuconver.items import WebsitesItem
from ltuconver.items import PersonItem
from scrapy import Spider
from scrapy.selector import Selector
from scrapy.http import Request
import bs4
class ConversationSpider(scrapy.Spider):
name = "urls"
allowed_domains = ["theconversation.com"]
start_urls = [
'http://theconversation.com/institutions/deakin-university/authors']
#URL grabber
def parse(self, response):
requests = []
people = Selector(response).xpath('///*[#id="experts"]/ul[*]/li[*]')
for person in people:
item = WebsitesItem()
item['url'] = 'http://theconversation.com/'+str(person.xpath('a/#href').extract())[4:-2]
self.logger.info('parseURL = %s',item['url'])
requests.append(Request(url=item['url'], callback=self.parseMainPage))
soup = bs4.BeautifulSoup(response.body, 'html.parser')
try:
nexturl = 'https://theconversation.com'+soup.find('span',class_='next').find('a')['href']
requests.append(Request(url=nexturl))
except:
pass
return requests
#go to URLs are grab the info
def parseMainPage(self, response):
person = Selector(response)
item = PersonItem()
item['name'] = str(person.xpath('//*[#id="outer"]/header/div/div[2]/h1/text()').extract())[3:-2]
item['occupation'] = str(person.xpath('//*[#id="outer"]/div/div[1]/div[1]/text()').extract())[11:-15]
item['art_count'] = int(str(person.xpath('//*[#id="outer"]/header/div/div[3]/a[1]/h2/text()').extract())[3:-3])
item['com_count'] = int(str(person.xpath('//*[#id="outer"]/header/div/div[3]/a[2]/h2/text()').extract())[3:-3])
And in my Settings, I have:
BOT_NAME = 'ltuconver'
SPIDER_MODULES = ['ltuconver.spiders']
NEWSPIDER_MODULE = 'ltuconver.spiders'
DEPTH_LIMIT=1
Apparently my six.py file was corrupt (or something like that). After swapping it out with the same file from a colleague, it started working again 8-\
I am able to scrape all the stories from the first page,my problem is how to move to the next page and continue scraping stories and name,kindly check my code below
# -*- coding: utf-8 -*-
import scrapy
from cancerstories.items import CancerstoriesItem
class MyItem(scrapy.Item):
name = scrapy.Field()
story = scrapy.Field()
class MySpider(scrapy.Spider):
name = 'cancerstories'
allowed_domains = ['thebreastcancersite.greatergood.com']
start_urls = ['http://thebreastcancersite.greatergood.com/clickToGive/bcs/stories/']
def parse(self, response):
rows = response.xpath('//a[contains(#href,"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
#myItem['name']=response.xpath('//h1[#class="headline"]/text()').extract()
text_raw = response.xpath('//div[#class="photoStoryBox"]/div/p/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
You could change your scrapy.Spider for a CrawlSpider, and use Rule and LinkExtractor to follow the link to the next page.
For this approach you have to include the code below:
...
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
...
rules = (
Rule(LinkExtractor(allow='\.\./stories;jsessionid=[0-9A-Z]+?page=[0-9]+')),
)
...
class MySpider(CrawlSpider):
...
This way, for each page you visit the spider will create a request for the next page (if present), follow it when finishes the execution for the parse method, and repeat the process again.
EDIT:
The rule I wrote is just to follow the next page link not to extract the stories, if your first approach works it's not necessary to change it.
Also, regarding the rule in your comment, SgmlLinkExtractor is deprecated so I recommend you to use the default link extractor, and the rule itself is not well defined.
When the parameter attrs in the extractor is not defined, it searchs links looking for the href tags in the body, which in this case looks like ../story/mother-of-4435 and not /clickToGive/bcs/story/mother-of-4435. That's the reason it doesn't find any link to follow.
you can follow next pages manually if you would use scrapy.spider class,example:
next_page = response.css('a.pageLink ::attr(href)').extract_first()
if next_page:
absolute_next_page_url = response.urljoin(next_page)
yield scrapy.Request(url=absolute_next_page_url, callback=self.parse)
Do not forget to rename your parse method to parse_start_url if you want to use CralwSpider class
I want to crawl a blog which has several categories of websites . Starting navigating the page from the first category, my goal is to collect every webpage by following the categories . I have collected the websites from the 1st category but the spider stops there , can't reach the 2nd category .
An example draft :
my code :
import scrapy
from scrapy.contrib.spiders import Rule, CrawlSpider
from scrapy.contrib.linkextractors import LinkExtractor
from final.items import DmozItem
class my_spider(CrawlSpider):
name = 'heart'
allowed_domains = ['greek-sites.gr']
start_urls = ['http://www.greek-sites.gr/categories/istoselides-athlitismos']
rules = (Rule(LinkExtractor(allow=(r'.*categories/.*', )), callback='parse', follow=True),)
def parse(self, response):
self.logger.info('Hi, this is an item page! %s', response.url)
categories = response.xpath('//a[contains(#href, "categories")]/text()').extract()
for category in categories:
item = DmozItem()
item['title'] = response.xpath('//a[contains(text(),"gr")]/text()').extract()
item['category'] = response.xpath('//div/strong/text()').extract()
return item
The problem is simple: the callback has to be different than parse, so I suggest you name your method parse_site for example and then you are ready to continue your scraping.
If you make the change below it will work:
rules = (Rule(LinkExtractor(allow=(r'.*categories/.*', )), callback='parse_site', follow=True),)
def parse_site(self, response):
The reason for this is described in the docs:
When writing crawl spider rules, avoid using parse as callback, since the CrawlSpider uses the parse method itself to implement its logic. So if you override the parse method, the crawl spider will no longer work.
I have to crawl a Web Site, so I use Scrapy to do it, but I need to pass a cookie to bypass the first page (which is a kind of login page, you choose you location)
I heard on the web that you need to do this with a base Spider (not a Crawl Spider), but I need to use a Crawl Spider to do my crawling, so what do I need to do?
At first a Base Spider? then launch my Crawl spider? But I don't know if cookie will be passed between them or how do I do it? How to launch a spider from another spider?
How to handle cookie? I tried with this
def start_requests(self):
yield Request(url='http://www.auchandrive.fr/drive/St-Quentin-985/', cookies={'auchanCook': '"985|"'})
But not working
My answer should be here, but the guy is really evasive and I don't know what to do.
First, you need to add open cookies in settings.py file
COOKIES_ENABLED = True
Here is my testing spider code for your reference. I tested it and passed
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.http import Request
from scrapy import log
class Stackoverflow23370004Spider(CrawlSpider):
name = 'auchandrive.fr'
allowed_domains = ["auchandrive.fr"]
target_url = "http://www.auchandrive.fr/drive/St-Quentin-985/"
def start_requests(self):
yield Request(self.target_url,cookies={'auchanCook': "985|"}, callback=self.parse_page)
def parse_page(self, response):
if 'St-Quentin-985' in response.url:
self.log("Passed : %r" % response.url,log.DEBUG)
else:
self.log("Failed : %r" % response.url,log.DEBUG)
You can run command to test and watch the console output:
scrapy crawl auchandrive.fr
I noticed that in your code snippet, you were using cookies={'auchanCook': '"985|"'}, instead of cookies={'auchanCook': "985|"}.
This should get you started:
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.http import Request
class AuchanDriveSpider(CrawlSpider):
name = 'auchandrive'
allowed_domains = ["auchandrive.fr"]
# pseudo-start_url
begin_url = "http://www.auchandrive.fr/"
# start URL used as shop selection
select_shop_url = "http://www.auchandrive.fr/drive/St-Quentin-985/"
rules = (
Rule(SgmlLinkExtractor(restrict_xpaths=('//ul[#class="header-menu"]',))),
Rule(SgmlLinkExtractor(restrict_xpaths=('//div[contains(#class, "vignette-content")]',)),
callback='parse_product'),
)
def start_requests(self):
yield Request(self.begin_url, callback=self.select_shop)
def select_shop(self, response):
return Request(url=self.select_shop_url, cookies={'auchanCook': "985|"})
def parse_product(self, response):
self.log("parse_product: %r" % response.url)
Pagination might be tricky.