I am attempting to add the follow url capability but can't seem to get it to work. I need to crawl all the pages. There are around 108 pages of the job listings. Thank you.
import scrapy
class JobItem(scrapy.Item):
# Data structure to store the title, company name and location of the job
title = scrapy.Field()
company = scrapy.Field()
location = scrapy.Field()
class PythonDocumentationSpider(scrapy.Spider):
name = 'pydoc'
start_urls = ['https://stackoverflow.com/jobs?med=site-ui&ref=jobs-tab']
def parse(self, response):
for follow_href in response.xpath('//h2[#class="fs-body2 job-details__spaced mb4"]/a/#href'):
follow_url = response.urljoin(follow_href.extract())
yield scrapy.Request(follow_url, callback=self.parse_page_title)
for a_el in response.xpath('//div[#class="-job-summary"]'):
section = JobItem()
section['title'] = a_el.xpath('.//a[#class="s-link s-link__visited job-link"]/text()').extract()[0]
span_texts = a_el.xpath('.//div[#class="fc-black-700 fs-body1 -company"]/span/text()').extract()
section['company'] = span_texts[0]
section['location'] = span_texts[1]
print(section['location'])
#print(type(section))
yield section
I am attempting to get the following url capability to work with my code and then be able to crawl the pages and store job postings in csv file.
.extract() return a list. In most cases you'll need to use .get() or .extract_first() instead if you don't need a list.
First you need to rewrite this part:
for follow_href in response.xpath('//h2[#class="fs-body2 job-details__spaced mb4"]/a/#href').getall(): # or .extract()
follow_url = response.urljoin(follow_href)
yield scrapy.Request(follow_url, callback=self.parse_page_title)
Related
Question: Is there a way to integrate BeautifulSoup's html5lib parser into a scrapy project--instead of the scrapy's default lxml parser?
Scrapy's parser fails (for some elements) of my scrape pages.
This only happens every 2 out of 20 pages.
As a fix, I've added BeautifulSoup's parser to the project (which works).
That said, I feel like I'm doubling the work with conditionals and multiple parsers...at a certain point, what's the reason for using Scrapy's parser? The code does work....it feels like a hack.
I'm no expert--is there a more elegant way to do this?
Much appreciation in advance
Update: Adding a middleware class to scrapy (from the python package scrapy-beautifulsoup) works like a charm. Apparently, lxml from Scrapy is not as robust as BeautifulSoup's lxml. I didn't have to resort to the html5lib parser--which is 30X+ slower.
class BeautifulSoupMiddleware(object):
def __init__(self, crawler):
super(BeautifulSoupMiddleware, self).__init__()
self.parser = crawler.settings.get('BEAUTIFULSOUP_PARSER', "html.parser")
#classmethod
def from_crawler(cls, crawler):
return cls(crawler)
def process_response(self, request, response, spider):
"""Overridden process_response would "pipe" response.body through BeautifulSoup."""
return response.replace(body=str(BeautifulSoup(response.body, self.parser)))
Original:
import scrapy
from scrapy.item import Item, Field
from scrapy.loader.processors import TakeFirst, MapCompose
from scrapy import Selector
from scrapy.loader import ItemLoader
from w3lib.html import remove_tags
from bs4 import BeautifulSoup
class SimpleSpider(scrapy.Spider):
name = 'SimpleSpider'
allowed_domains = ['totally-above-board.com']
start_urls = [
'https://totally-above-board.com/nefarious-scrape-page.html'
]
custom_settings = {
'ITEM_PIPELINES': {
'crawler.spiders.simple_spider.Pipeline': 400
}
}
def parse(self, response):
yield from self.parse_company_info(response)
yield from self.parse_reviews(response)
def parse_company_info(self, response):
print('parse_company_info')
print('==================')
loader = ItemLoader(CompanyItem(), response=response)
loader.add_xpath('company_name',
'//h1[contains(#class,"sp-company-name")]//span//text()')
yield loader.load_item()
def parse_reviews(self, response):
print('parse_reviews')
print('=============')
# Beautiful Soup
selector = Selector(response)
# On the Page (Total Reviews) # 49
search = '//span[contains(#itemprop,"reviewCount")]//text()'
review_count = selector.xpath(search).get()
review_count = int(float(review_count))
# Number of elements Scrapy's LXML Could find # 0
search = '//div[#itemprop ="review"]'
review_element_count = len(selector.xpath(search))
# Use Scrapy or Beautiful Soup?
if review_count > review_element_count:
# Try Beautiful Soup
soup = BeautifulSoup(response.text, "lxml")
root = soup.findAll("div", {"itemprop": "review"})
for review in root:
loader = ItemLoader(ReviewItem(), selector=review)
review_text = review.find("span", {"itemprop": "reviewBody"}).text
loader.add_value('review_text', review_text)
author = review.find("span", {"itemprop": "author"}).text
loader.add_value('author', author)
yield loader.load_item()
else:
# Try Scrapy
review_list_xpath = '//div[#itemprop ="review"]'
selector = Selector(response)
for review in selector.xpath(review_list_xpath):
loader = ItemLoader(ReviewItem(), selector=review)
loader.add_xpath('review_text',
'.//span[#itemprop="reviewBody"]//text()')
loader.add_xpath('author',
'.//span[#itemprop="author"]//text()')
yield loader.load_item()
yield from self.paginate_reviews(response)
def paginate_reviews(self, response):
print('paginate_reviews')
print('================')
# Try Scrapy
selector = Selector(response)
search = '''//span[contains(#class,"item-next")]
//a[#class="next"]/#href
'''
next_reviews_link = selector.xpath(search).get()
# Try Beautiful Soup
if next_reviews_link is None:
soup = BeautifulSoup(response.text, "lxml")
try:
next_reviews_link = soup.find("a", {"class": "next"})['href']
except Exception as e:
pass
if next_reviews_link:
yield response.follow(next_reviews_link, self.parse_reviews)
It’s a common feature request for Parsel, Scrapy’s library for XML/HTML scraping.
However, you don’t need to wait for such a feature to be implemented. You can fix the HTML code using BeautifulSoup, and use Parsel on the fixed HTML:
from bs4 import BeautifulSoup
# …
response = response.replace(body=str(BeautifulSoup(response.body, "html5lib")))
You can get a charset error using the #Gallaecio's answer, if the original page was not utf-8 encoded, because the response has set to other encoding.
So, you must first switch the encoding.
In addition, there may be a problem of character escaping.
For example, if the character < is encountered in the text of html, then it must be escaped as <. Otherwise, "lxml" will delete it and the text near it, considering it an erroneous html tag.
"html5lib" escapes characters, but is slow.
response = response.replace(encoding='utf-8',
body=str(BeautifulSoup(response.body, 'html5lib')))
"html.parser" is faster, but from_encoding must also be specified (to example 'cp1251').
response = response.replace(encoding='utf-8',
body=str(BeautifulSoup(response.body, 'html.parser', from_encoding='cp1251')))
I am learning Scrapy. Now I just try to scrapy items and when I call spider:
planefinder]# scrapy crawl planefinder -o /User/spider/planefinder/pf.csv -t csv
it shows tech information and no scraped content (Crawled 0 pages .... etc), and it returns an empty csv file.
The problem is when i test xpath in scrapy shell it works:
>>> from scrapy.selector import Selector
>>> sel = Selector(response)
>>> flights = sel.xpath("//div[#class='col-md-12'][1]/div/div/table//tr")
>>> items = []
>>> for flt in flights:
... item = flt.xpath("td[1]/a/#href").extract_first()
... items.append(item)
...
>>> items
The following is my planeFinder.py code:
# -*-:coding:utf-8 -*-
from scrapy.spiders import CrawlSpider
from scrapy.selector import Selector, HtmlXPathSelector
from planefinder.items import arr_flt_Item, dep_flt_Item
class planefinder(CrawlSpider):
name = 'planefinder'
host = 'https://planefinder.net'
start_url = ['https://planefinder.net/data/airport/PEK/']
def parse(self, response):
arr_flights = response.xpath("//div[#class='col-md-12'][1]/div/div/table//tr")
dep_flights = response.xpath("//div[#class='col-md-12'][2]/div/div/table//tr")
for flight in arr_flights:
arr_item = arr_flt_Item()
arr_flt_url = flight.xpath('td[1]/a/#href').extract_first()
arr_item['arr_flt_No'] = flight.xpath('td[1]/a/text()').extract_first()
arr_item['STA'] = flight.xpath('td[2]/text()').extract_first()
arr_item['From'] = flight.xpath('td[3]/a/text()').extract_first()
arr_item['ETA'] = flight.xpath('td[4]/text()').extract_first()
yield arr_item
Please before going to CrawlSpider please check the docs for Spiders, some of the issues I've found were:
Instead of host use allowed_domains
Instead of start_url use start_urls
It seem that the page needs to have some cookies set or maybe it's using some kind of basic anti-bot protection, and you need to land somewhere else first.
Try this (I've also changed a bit :
# -*-:coding:utf-8 -*-
from scrapy import Field, Item, Request
from scrapy.spiders import CrawlSpider, Spider
class ArrivalFlightItem(Item):
arr_flt_no = Field()
arr_sta = Field()
arr_from = Field()
arr_eta = Field()
class PlaneFinder(Spider):
name = 'planefinder'
allowed_domains = ['planefinder.net']
start_urls = ['https://planefinder.net/data/airports']
def parse(self, response):
yield Request('https://planefinder.net/data/airport/PEK', callback=self.parse_flight)
def parse_flight(self, response):
flights_xpath = ('//*[contains(#class, "departure-board") and '
'./preceding-sibling::h2[contains(., "Arrivals")]]'
'//tr[not(./th) and not(./td[#class="spacer"])]')
for flight in response.xpath(flights_xpath):
arrival = ArrivalFlightItem()
arr_flt_url = flight.xpath('td[1]/a/#href').extract_first()
arrival['arr_flt_no'] = flight.xpath('td[1]/a/text()').extract_first()
arrival['arr_sta'] = flight.xpath('td[2]/text()').extract_first()
arrival['arr_from'] = flight.xpath('td[3]/a/text()').extract_first()
arrival['arr_eta'] = flight.xpath('td[4]/text()').extract_first()
yield arrival
The problem here is not understanding correctly which "Spider" to use, as Scrapy offers different custom ones.
The main one, and the one you should be using is the simple Spider and not CrawlSpider, because CrawlSpider is used for a more deep and intensive search into forums, blogs, etc.
Just change the type of spider to:
from scrapy import Spider
class plane finder(Spider):
...
Check the value of ROBOTSTXT_OBEY in your settings.py file. By default it's set to True (but not when you run shell). Set it to False if you wan't to disobey robots.txt file.
I'm trying to extract the text from this Xpath:
//*/li[contains(., "Full Name")]/span/text()
from this webpage:
http://votesmart.org/candidate/biography/56110/norma-smith#.V9SwdZMrKRs
I've tested it in Google Chrome's Console (which works), as with many other variations of the Xpath, but I can't get it to work with Scrapy. My code only returns "{}".
Here's where I have been testing it in my code, for context:
def parse_bio(self, response):
loader = response.meta['loader']
fullnameValue = response.xpath('//*/li[contains(., "Full Name")]/span/text()').extract()
loader.add_value('fullName', fullnameValue)
return loader.load_item()
The problem isn't my code (I don't think), it works fine with other (very broad) Xpath selectors. But I'm not sure what's wrong with the Xpath. I have JavaScript disabled, if that makes a difference.
Any help would be great!
Edit: Here is the rest of the code to make it more clear:
from scrapy import Spider, Request, Selector
from votesmart.items import LegislatorsItems, TheLoader
class VSSpider(Spider):
name = "vs"
allowed_domains = ["votesmart.org"]
start_urls = ["https://votesmart.org/officials/WA/L/washington-state-legislative"]
def parse(self, response):
for href in response.xpath('//h5/a/#href').extract():
person_url = response.urljoin(href)
yield Request(person_url, callback=self.candidatesPoliticalSummary)
def candidatesPoliticalSummary(self, response):
item = LegislatorsItems()
l = TheLoader(item=LegislatorsItems(), response=response)
...
#populating items with item loader. works fine
# create right bio url and pass item loader to it
bio_url = response.url.replace('votesmart.org/candidate/',
'votesmart.org/candidate/biography/')
return Request(bio_url, callback=self.parse_bio, meta={'loader': l})
def parse_bio(self, response):
loader = response.meta['loader']
print response.request.url
loader.add_xpath('fullName', '//*/li[contains(., "Full Name")]/span/text()')
return loader.load_item()
I figured out my problem! Many pages on the site were login protected, and I wasn't able to scrape from pages that I couldn't access in the first place. Scrapy's form request did the trick. Thanks for all the help (especially the suggestion of using view(response), which is super helpful).
The expression is working for me in the shell perfectly as is:
$ scrapy shell "http://votesmart.org/candidate/biography/56110/norma-smith#.V9SwdZMrKRs"
In [1]: response.xpath('//*/li[contains(., "Full Name")]/span/text()').extract()
Out[1]: [u'Norma Smith']
Try using the add_xpath() method instead:
loader.add_xpath('fullName', '//*/li[contains(., "Full Name")]/span/text()')
I am scraping producthunt.com using Scrapy with Python3 on Win10. I am confused by my code behaviour, which duplicates some fields in output data.
Can anyone point at the reason of that and suggest a solution?
Code:
http://pastebin.com/VvFGCmDJ
Sample of the output:
http://pastebin.com/ffx0HN54
I haven't run your code but creating the Item instance definitely needs to be inside the for loop:
...
def parse(self, response):
jsonresponse = json.loads(response.body_as_unicode())
topic = jsonresponse['posts']
for post in topic:
service = ProducthuntItem()
service['name'] = post['name'].replace(";", " ")
...
I am scraping the following web site https://www2.woolworthsonline.com.au
My first step is to get a list of product categories, which I can do.
Then I need to get sub-categories. The sub-categories seem to be dynamically generated. I have set up what I thought to be the right header and body information for the request and a small test call-back to see if the request is working correctly. My code never gets to the callback, so presumably there is something wrong with the request
def parse(self, response):
# Get links to the categories
categories_links = response.xpath('//a[#class="navigation-link"]').re(r'href="(\S+)"')
for link in categories_links:
# Generate and yield a request for the sub-categories
get_request_headers = dict()
get_request_headers['Accept'] = 'application/xml, text/xml, */*; q=0.01'
get_request_headers['Accept-Encoding'] = 'gzip, deflate, sdch'
get_request_headers['Accept-Language'] = 'en-US,en;q=0.8'
get_request_headers['Connection'] = 'keep-alive'
get_request_body = urllib.urlencode(
{'_mode' : 'ajax',
'_ajaxsource' : 'navigation-panel',
'_referrer' : link,
'_bannerViews' : '6064',
'_' : '1429428492880'}
)
url_link = 'https://www2.woolworthsonline.com.au'+link
yield Request(url=url_link, callback=self.subcategories, headers = get_request_headers, method='POST', body = get_request_body, meta={'category_link' : link} )
return
def subcategories(self, response):
print "sub-categories test: ", response.url
return
Try this out,
BASE_URL = 'https://www2.woolworthsonline.com.au'
def parse(self, response):
categories = response.xpath(
'//a[#class="navigation-link"]/#href').extract()
for link in categories:
yield Request(url=self.BASE_URL + link, callback=parse_subcategory)
def parse_subcategory(self, response):
sub_categories = response.xpath(
'//li[#class="navigation-node navigation-category selected"]/ul/li/span/a/#href').extract()
for link in sub_categories:
yield Request(url=self.BASE_URL + link, callback=parse_products)
def parse_products(self, response):
# here you will get the list of products based on the subcategory
# extract the product details here
First we extract the category list from the start-url in parse function
Then give request to extracted category-url ( we have to provide BASE_URL along with the extracted category-url, since that urls are given as relative urls not the absolute one)
In the callback function (here parse_subcategory) we can get the response of each category-url
Likewise we are doing the same thing for sub-categories also
Finally extract the product details