Skip to content

crawlersNoticias
crawlersNoticias
Commit 620c10e0 authored by Renán Sosa Guillen's avatar Renán Sosa Guillen
Browse files
Options

deleted

parent 04edd575
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 652 deletions
descarga_hacia_atras/foraneos/tribunaHn_deprecated/scrapy.cfg deleted 100644 → 0
View file @ 04edd575
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = tribunaHn.settings
[deploy]
#url = http://localhost:6800/
project = tribunaHn
descarga_hacia_atras/foraneos/tribunaHn_deprecated/tribunaHn/items.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class NoticiasItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
text = scrapy.Field()
date = scrapy.Field()
location = scrapy.Field()
author = scrapy.Field()
topic = scrapy.Field()
url = scrapy.Field()
descarga_hacia_atras/foraneos/tribunaHn_deprecated/tribunaHn/middlewares.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class TribunahnSpiderMiddleware(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(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(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(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(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)
descarga_hacia_atras/foraneos/tribunaHn_deprecated/tribunaHn/pipelines.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from collections import OrderedDict
class JsonWriterPipeline(object):
def __init__(self, filename):
self.filename = filename
@classmethod
def from_crawler(cls, crawler):
# Here you get whatever value was passed through the "filename" command line parameter
settings = crawler.settings
filename = settings.get('filename')
# Instantiate the pipeline with the file name
return cls(filename)
def open_spider(self, spider):
self.counter = 0
self.file = open(self.filename, 'w')
self.file.write("[")
def close_spider(self, spider):
self.file.write("]")
self.file.close()
def process_item(self, item, spider):
# print("this is my item", item)
row = []
try:
row.append(("date", item['date']))
except:
pass
try:
row.append(("topic", item['topic']))
except:
pass
try:
row.append(("title", item['title']))
except:
pass
try:
row.append(("author", item['author']))
except:
pass
try:
row.append(("location", item['location']))
except:
pass
try:
row.append(("text", item['text']))
except:
pass
try:
row.append(("url", item['url']))
except:
pass
line = OrderedDict(row)
self.counter += 1
if self.counter == 1:
self.file.write(json.dumps(line))
elif self.counter > 1:
self.file.write(",\n" + json.dumps(line))
return item
descarga_hacia_atras/foraneos/tribunaHn_deprecated/tribunaHn/settings.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Scrapy settings for tribunaHn project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'tribunaHn'
SPIDER_MODULES = ['tribunaHn.spiders']
NEWSPIDER_MODULE = 'tribunaHn.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'tribunaHn (+http://www.yourdomain.com)'
# Obey robots.txt rules
# ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.5
# 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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'tribunaHn.middlewares.TribunahnSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'tribunaHn.middlewares.MyCustomDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'tribunaHn.pipelines.JsonWriterPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://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 http://scrapy.readthedocs.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'
descarga_hacia_atras/foraneos/tribunaHn_deprecated/tribunaHn/spiders/__init__.py deleted 100644 → 0
View file @ 04edd575
# 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.
descarga_hacia_atras/foraneos/tribunaHn_deprecated/tribunaHn/spiders/noticias.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
"""
===============================================================================
THIS VERSION OF La Tribuna Honduras IS NOW DEPRECATED SINCE THE SITE'S WEB PAGE
CHANGE ITS ACCESS TO ACCES BY DAY.
THE NEW VERSION CAN BE FOUNd IN THE descarga_por_dia/foraneos FOLDER.
===============================================================================
"""
import scrapy, re, json
from datetime import date
from tribunaHn.items import NoticiasItem
"""
MEDIO:
La Tribuna, Honduras
USO:
// Si se quiere obtener todas las noticias desde las más actuales hasta las más antiguas. //
scrapy crawl noticias --nolog -s filename=noticias.json
-------------------------------------------------------------------------------------------------
// Si se quiere obtener todas las noticias desde las más actuales hasta una fecha específica. //
scrapy crawl noticias --nolog -s filename=noticias.json -a year=2018 -a month=2 -a day=29
-------------------------------------------------------------------------------------------------
Después será necesario hacer uso del archivo parse_date_files.py para que las noticias contenidas
en noticias.json sean separadas en archivos por fecha.
"""
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
DAT_RE = re.compile(r'\d{4}\/\d{2}\/\d{2}')
class ImportantData(scrapy.Item):
section = scrapy.Field()
page = scrapy.Field()
class QuotesSpider(scrapy.Spider):
name = "noticias"
def start_requests(self):
self.year = getattr(self, "year", None)
self.month = getattr(self, "month", None)
self.day = getattr(self, "day", None)
if self.year is not None and self.month is not None and self.day is not None:
self.stopDate = date(int(self.year), int(self.month), int(self.day))
else:
self.stopDate = None
baseURL = "http://www.latribuna.hn/"
sectionList = ["noticias", "honduras", "sociedad", "cafeteando", "dejenme-decirles", "desde-usa",
"ecomentarios", "el-cambio-climatico", "el-dossier-de-atenea", "enfoques",
"pecadillos-idiomaticos", "pildoritas", "columnistas", "editorial", "tribuna-del-pueblo",
"anales-historicos", "cine", "dejando-huellas", "dia-7", "dominicales", "done-un-aula",
"especiales-lt", "la-cobra-pregunta", "la-tribuna-agropecuaria", "la-tribuna-cultural",
"nuestro-orgullo", "turismo"]
# sectionList = ["noticias"]
for s in sectionList:
yield scrapy.Request(url=baseURL + s, callback=self.parse)
def parse(self, response):
CONTINUE_SEARCHING = True
linkList = response.xpath('//div[@id="main"]').css('article.linkbox').xpath('./a[@itemprop="url"]/@href').extract()
linkList.extend(response.xpath('//div[@id="main"]').css('div.bottom-margin').css('div.col-sm-6').xpath('./h3/a[@itemprop="url"]/@href').extract())
if self.stopDate is None:
for link in linkList:
yield scrapy.Request(url=link, callback=self.parse_item)
else:
for link in linkList:
res = DAT_RE.search(link)
if res:
dat = map(int, res.group(0).split("/"))
newsDate = date(dat[0], dat[1], dat[2])
if newsDate >= self.stopDate:
yield scrapy.Request(url=link, callback=self.parse_item)
else:
CONTINUE_SEARCHING = False
break
if CONTINUE_SEARCHING:
nextPage = response.xpath('//span[@class="next"]/a/@href').extract_first()
if nextPage is not None:
yield scrapy.Request(url=nextPage, callback=self.parse)
def parse_item(self, response):
item = NoticiasItem()
text = ''
"La fecha obtenida ya incluye formato y zona horaria"
item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
item['title'] = remove_tags(response.xpath('//header/h1[@itemprop="name"]').extract_first())
try:
topic = response.xpath('//aside[@class="tags"]/ul/li/a/text()').extract()[0]
except:
topic = None
item['topic'] = topic
for p in response.css('div.article-post-content').css('p').extract():
text += remove_tags(p) + "\n"
item['text'] = text.strip()
item['url'] = response.url
yield item
descarga_hacia_atras/laJornadaBC2/laJornadaBC2/items.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class Lajornadabc2Item(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
descarga_hacia_atras/laJornadaBC2/laJornadaBC2/middlewares.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
class Lajornadabc2SpiderMiddleware(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(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(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(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(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)
descarga_hacia_atras/laJornadaBC2/laJornadaBC2/pipelines.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
class Lajornadabc2Pipeline(object):
def process_item(self, item, spider):
return item
descarga_hacia_atras/laJornadaBC2/laJornadaBC2/settings.py deleted 100644 → 0
View file @ 04edd575
# -*- coding: utf-8 -*-
# Scrapy settings for laJornadaBC2 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
# http://doc.scrapy.org/en/latest/topics/settings.html
# http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'laJornadaBC2'
SPIDER_MODULES = ['laJornadaBC2.spiders']
NEWSPIDER_MODULE = 'laJornadaBC2.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'laJornadaBC2 (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.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 http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'laJornadaBC2.middlewares.Lajornadabc2SpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornadaBC2.middlewares.MyCustomDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}
# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
# 'laJornadaBC2.pipelines.Lajornadabc2Pipeline': 300,
#}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://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 http://scrapy.readthedocs.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'
descarga_hacia_atras/laJornadaBC2/laJornadaBC2/spiders/__init__.py deleted 100644 → 0
View file @ 04edd575
# 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.
descarga_hacia_atras/laJornadaBC2/laJornadaBC2/spiders/noticias.py deleted 100644 → 0
View file @ 04edd575
import scrapy, re
"""
Esta version descarga todas las noticias contenidas en la pagina, sin necesidad
de una fecha especifica.
USO:
scrapy crawl noticias -t json --nolog -o noticias.json
Genera un archivo JSON con todas las noticias disponibles. El archivo 'parse_date_file.py'
puede servir para clasificar dichas noticias en sus respectivas fechas.
"""
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
class NoticiasItem(scrapy.Item):
title = scrapy.Field()
text = scrapy.Field()
date = scrapy.Field()
location = scrapy.Field()
author = scrapy.Field()
topic = scrapy.Field()
url = scrapy.Field()
class QuotesSpider(scrapy.Spider):
name = 'noticias'
def start_requests(self):
self.baseURL = 'http://jornadabc.mx'
section_list = ['baja-california', 'chihuahua', 'mexico', 'mundo',
'cultura', 'espectaculos', 'deportes']
for section in section_list:
yield scrapy.Request(url=self.baseURL+'/seccion/'+section, callback=self.parse)
def parse(self, response):
pagination = response.xpath('//ul[@class="pager"]/li[@class="pager-last odd last"]/a/@href').extract()
if ( len(pagination) > 0 ):
section = response.url[response.url.rfind('/')+1:]
pagination = pagination[0]
pages = int(pagination[pagination.rfind('=')+1:])
for page in range(0, pages):
if ( page == 0 ):
yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
else:
yield scrapy.Request(url=self.baseURL+'/seccion/'+section+'?page='+str(page), callback=self.parse_page, dont_filter=True)
else:
yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
def parse_page(self, response):
section = response.url[response.url.rfind('/')+1:]
section = section[:section.rfind('?')]
if ( section == 'espectaculos' or section == 'deportes' ):
link_list = response.xpath('//*[@class="region region-soft-first"]').css('div.views-row').xpath('./*[@class="views-field views-field-title"]/span[@class="field-content"]/a/@href').extract()
else:
link_list = response.xpath('//*[@class="region region-hard-first"]').css('div.views-row').xpath('./*[@class="views-field views-field-title"]/span[@class="field-content"]/a/@href').extract()
if len(link_list) <= 0:
link_list = response.xpath('//*[@class="view-content"]').css('div.views-row').xpath('./*[@class="views-field views-field-title"]/span[@class="field-content"]/a/@href').extract()
for link in link_list:
yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item)
def parse_item(self, response):
item = NoticiasItem()
text = ''
## la fecha de las noticias ya incluye la zona horaria
item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
title = response.xpath('//*[@class="block-content"]/h1/a/text()').extract()
if ( len(title) > 0 ):
item['title'] = title[0]
else:
item['title'] = response.xpath('//*[@class="block-content"]/h1/text()').extract_first()
item['topic'] = response.xpath('//span[@class="section"]/text()').extract_first()
for paragraph in response.xpath('//*[@class="field-item even"]/p/text()').extract():
text += paragraph
item['text'] = text
item['url'] = response.url
# print item['title']
yield item
descarga_hacia_atras/laJornadaBC2/scrapy.cfg deleted 100644 → 0
View file @ 04edd575
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = laJornadaBC2.settings
[deploy]
#url = http://localhost:6800/
project = laJornadaBC2
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