Commit a0f4ab88 authored by Orkut Karacalik's avatar Orkut Karacalik
Browse files

first commit

parent 085c9437
.directory
*.pyc
*.ini
*.json
\ No newline at end of file
# H-Index of Conference Speakers
\ No newline at end of file
# H-Index of Conference Speakers
## Methodology
1. Select field in CS
2. Search for external links
3. Use google to search in-site for keywords ['speaker', ...]
4. Get pages and look for keywords ['bio', 'biography', ...]
5. Save available data
### Python Packages
1. scrapy
2. spacy
3.
\ No newline at end of file
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import json
from functools import reduce
with open('conferences.json') as f:
conferences = json.load(f)
links = reduce(lambda x, y: x + y, list(map(lambda x: x['conferences'], conferences)))
links.sort()
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html
from scrapy import Item, Field
class ConferenceItem(Item):
field = Field()
subfield = Field()
name = Field()
link = Field()
conferences = Field()
class ConferenceWebsite(Item):
link = Field()
speakers = Field()
class AuthorProfileItem(Item):
date = Field()
name = Field()
citations = Field()
h_index = Field()
citations_last_5_year = Field()
h_index_lat_5_year = Field()
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class CssSpiderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the spider middleware does not modify the
# passed objects.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_spider_input(self, response, spider):
# Called for each response that goes through the spider
# middleware and into the spider.
# Should return None or raise an exception.
return None
def process_spider_output(self, response, result, spider):
# Called with the results returned from the Spider, after
# it has processed the response.
# Must return an iterable of Request, dict or Item objects.
for i in result:
yield i
def process_spider_exception(self, response, exception, spider):
# Called when a spider or process_spider_input() method
# (from other spider middleware) raises an exception.
# Should return either None or an iterable of Response, dict
# or Item objects.
pass
def process_start_requests(self, start_requests, spider):
# Called with the start requests of the spider, and works
# similarly to the process_spider_output() method, except
# that it doesn’t have a response associated.
# Must return only requests (not items).
for r in start_requests:
yield r
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
class CssDownloaderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the downloader middleware does not modify the
# passed objects.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_request(self, request, spider):
# Called for each request that goes through the downloader
# middleware.
# Must either:
# - return None: continue processing this request
# - or return a Response object
# - or return a Request object
# - or raise IgnoreRequest: process_exception() methods of
# installed downloader middleware will be called
return None
def process_response(self, request, response, spider):
# Called with the response returned from the downloader.
# Must either;
# - return a Response object
# - return a Request object
# - or raise IgnoreRequest
return response
def process_exception(self, request, exception, spider):
# Called when a download handler or a process_request()
# (from other downloader middleware) raises an exception.
# Must either:
# - return None: continue processing this exception
# - return a Response object: stops process_exception() chain
# - return a Request object: stops process_exception() chain
pass
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
class CssPipeline(object):
def process_item(self, item, spider):
return item
# -*- coding: utf-8 -*-
# Scrapy settings for css project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# https://doc.scrapy.org/en/latest/topics/settings.html
# https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'css'
SPIDER_MODULES = ['css.spiders']
NEWSPIDER_MODULE = 'css.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'css (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
#COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'css.middlewares.CssSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'css.middlewares.CssDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
# 'css.pipelines.CssPipeline': 300,
#}
# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
# This package will contain the spiders of your Scrapy project
#
# Please refer to the documentation for information on how to create and manage
# your spiders.
# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import HtmlResponse
from scrapy.http.request import Request
from css.items import ConferenceItem, ConferenceWebsite
class CsConferencesSpider(scrapy.Spider):
name = 'cs-conferences'
allowed_domains = ['en.wikipedia.org']
start_urls = [
'https://en.wikipedia.org/wiki/List_of_computer_science_conferences'
]
def parse(self, response):
items = response.xpath("// h2[span[contains(@class, 'mw-headline')]] | //h3[span[contains(@class, 'mw-headline')]] | //*[*/ul/li/a][@class != 'toc']/ul/li/a").extract()
currentField = "-"
currentSubfield = "-"
for (index, item) in enumerate(items):
htmlResponse = self.__convert_html__(item)
if htmlResponse.xpath("//h2/span[contains(@class, 'mw-headline')]/text()").extract_first() is not None:
currentField = htmlResponse.xpath(
"//h2/span[contains(@class, 'mw-headline')]/text()").extract_first()
currentSubfield = "-"
elif htmlResponse.xpath("//h3/span[contains(@class, 'mw-headline')]/text()").extract_first() is not None:
currentSubfield = htmlResponse.xpath(
"//h3/span[contains(@class, 'mw-headline')]/text()").extract_first()
else:
if currentField == 'See also':
break
else:
confItem = ConferenceItem()
confItem['field'] = currentField
confItem['subfield'] = currentSubfield
confItem['name'] = htmlResponse.xpath("//a/text()").extract_first()
confItem['link'] = response.urljoin(htmlResponse.xpath("//a/@href").extract_first())
yield Request(confItem['link'], meta={'confItem': confItem}, callback=self.parse_conferences)
def parse_conferences(self, response):
confItem = response.meta['confItem']
links = response.xpath(
"//div[@id='bodyContent']//a[starts-with(@href, 'http') and not(contains(@href, 'wikipedia')) ]/@href").extract()
confItem['conferences'] = [ ConferenceWebsite(link=l, speakers=[]) for l in links]
yield confItem
def __convert_html__(self, item):
return HtmlResponse(url="https://en.wikipedia.org/wiki/List_of_computer_science_conferences", body=item, encoding="utf-8")
# -*- coding: utf-8 -*-
import scrapy
import datetime
from css.items import AuthorProfileItem
class HIndexSpider(scrapy.Spider):
name = 'h-index'
allowed_domains = ['scholar.google.com']
start_urls = [
'https://scholar.google.com/citations?user=QvpcUn8AAAAJ&hl=en'
]
def parse(self, response):
now = datetime.datetime.now()
name = response.css("#gsc_prf_in::text").extract_first()
citation_table = response.css(".gsc_rsb_std::text").extract()
if len(citation_table) > 0:
item = AuthorProfileItem()
item['date'] = now.strftime("%Y-%m-%d")
item['name'] = name
item['citations'] = citation_table[0]
item['citations_last_5_year'] = citation_table[1]
item['h_index'] = citation_table[2]
item['h_index_lat_5_year'] = citation_table[3]
yield item
# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import HtmlResponse
from scrapy.http.request import Request
class SpeakersSpider(scrapy.Spider):
name = 'speakers'
start_urls = ['http://www.ase2014.org/']
def parse(self, response):
keywords = ['keynotes', 'speaker', 'invited', 'program']
# via keywords
links = response.xpath('//a[descendant::*[re:match(text(), "keynotes|speaker|invited|program", "i")]]/@href').extract()
for link in links:
nextPath = link if link.startswith('http') else response.urljoin(link)
yield Request(nextPath, meta={'link': nextPath}, callback=self.parse_names)
# otherwise look for all links
def parse_names(self, response):
link = response.meta['link']
speakers = response.xpath('//*[re:match(text(), "^prof|^dr", "i")]/text()').extract()
yield {
'link': link,
'speakers': speakers
}
# text = remove_tags(replace_escape_chars(strip_html5_whitespace(response.text)))
# nlp = spacy.load('xx')
# doc = nlp(text)
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.io/en/latest/deploy.html
[settings]
default = css.settings
[deploy]
#url = http://localhost:6800/
project = css
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment