Skip to content

crawlersNoticias
crawlersNoticias
Commit eba6fe5b authored by Renán Sosa Guillen's avatar Renán Sosa Guillen
Browse files
Options

deleted

parent 15cbb498
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 686 deletions
descarga_hacia_atras/laJornadaMaya2/laJornadaMaya2/items.py deleted 100644 → 0
View file @ 15cbb498
# -*- 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 Lajornadamaya2Item(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
descarga_hacia_atras/laJornadaMaya2/laJornadaMaya2/middlewares.py deleted 100644 → 0
View file @ 15cbb498
# -*- 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 Lajornadamaya2SpiderMiddleware(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/laJornadaMaya2/laJornadaMaya2/pipelines.py deleted 100644 → 0
View file @ 15cbb498
# -*- 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 Lajornadamaya2Pipeline(object):
def process_item(self, item, spider):
return item
descarga_hacia_atras/laJornadaMaya2/laJornadaMaya2/settings.py deleted 100644 → 0
View file @ 15cbb498
# -*- coding: utf-8 -*-
# Scrapy settings for laJornadaMaya2 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 = 'laJornadaMaya2'
SPIDER_MODULES = ['laJornadaMaya2.spiders']
NEWSPIDER_MODULE = 'laJornadaMaya2.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'laJornadaMaya2 (+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 = {
# 'laJornadaMaya2.middlewares.Lajornadamaya2SpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornadaMaya2.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 = {
# 'laJornadaMaya2.pipelines.Lajornadamaya2Pipeline': 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/laJornadaMaya2/laJornadaMaya2/spiders/__init__.py deleted 100644 → 0
View file @ 15cbb498
# 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/laJornadaMaya2/laJornadaMaya2/spiders/noticias.py deleted 100644 → 0
View file @ 15cbb498
import scrapy, json, re
from datetime import datetime, date, timedelta, tzinfo
"""
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 UTC(tzinfo):
"""clase para el 'time zone' (zona horaria)"""
def utcoffset(self, dt):
# zona horaria para yucatan (centro de mexico): utc-6
return timedelta(hours=-6)
def tzname(self, dt):
# nombre de la zona horaria
return 'UTC-6'
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.tz = UTC()
self.baseURL = 'https://www.lajornadamaya.mx'
section_list = [('yucatan',123,'Yucatan'), ('quintana-roo',52,'Quintana Roo'),
('campeche',32,'Campeche'), ('opinion',0,'Opinion'), ('deportes',91,'Deportes'),
('nacional',100,'Nacional'), ('internacional',87,'Internacional')]
# section_list = [('opinion',0,'Opinion')]
for section in section_list:
self.section = section
if not ( section[0] == 'opinion' ):
for page in range(0,section[1]+1):
yield scrapy.Request(url=self.baseURL+'/'+section[0]+'?p='+str(page), callback=self.parse)
else:
yield scrapy.Request(url=self.baseURL+'/notas?opinion', callback=self.parse)
def parse(self, response):
json_response = json.loads(response.text)
if not ( self.section[0] == 'opinion' ):
json_list = json_response
else:
json_list = json_response['articles']
for line in json_list:
item = NoticiasItem()
d = line['publishDate']
if len(d) == 10:
d = map(int, d.split('-'))
d = datetime(d[0], d[1], d[2], tzinfo=self.tz).isoformat('T')
elif len(d) == 19:
d, t = d.split(' ')
d = map(int, d.split('-'))
t = map(int, t.split(':'))
d = datetime(d[0],d[1],d[2],t[0],t[1],t[2],tzinfo=self.tz).isoformat('T')
item['date'] = d
item['topic'] = self.section[2]
item['title'] = line['name']
if not ( self.section[0] == 'opinion' ):
request = scrapy.Request(url=self.baseURL+line['url'], callback=self.parse_item)
else:
request = scrapy.Request(url=self.baseURL+'/'+line['publishDate'][:line['publishDate'].rfind(' ')]+'/'+line['uriComponent'], callback=self.parse_item)
request.meta['item'] = item
yield request
def parse_item(self, response):
item = response.meta['item']
text = ''
for paragraph in response.xpath('//*[@class="txt"]').extract():
text += remove_tags(paragraph) + '\n'
item['text'] = text
item['url'] = response.url
# print item['title']
yield item
descarga_hacia_atras/laJornadaMaya2/scrapy.cfg deleted 100644 → 0
View file @ 15cbb498
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = laJornadaMaya2.settings
[deploy]
#url = http://localhost:6800/
project = laJornadaMaya2
descarga_hacia_atras/laJornadaMaya_deprecated/laJornadaMaya/items.py deleted 100644 → 0
View file @ 15cbb498
# -*- 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 LajornadamayaItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
descarga_hacia_atras/laJornadaMaya_deprecated/laJornadaMaya/middlewares.py deleted 100644 → 0
View file @ 15cbb498
# -*- 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 LajornadamayaSpiderMiddleware(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/laJornadaMaya_deprecated/laJornadaMaya/pipelines.py deleted 100644 → 0
View file @ 15cbb498
# -*- 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 LajornadamayaPipeline(object):
def process_item(self, item, spider):
return item
descarga_hacia_atras/laJornadaMaya_deprecated/laJornadaMaya/settings.py deleted 100644 → 0
View file @ 15cbb498
# -*- coding: utf-8 -*-
# Scrapy settings for laJornadaMaya 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 = 'laJornadaMaya'
SPIDER_MODULES = ['laJornadaMaya.spiders']
NEWSPIDER_MODULE = 'laJornadaMaya.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'laJornadaMaya (+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 = {
# 'laJornadaMaya.middlewares.LajornadamayaSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornadaMaya.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 = {
# 'laJornadaMaya.pipelines.LajornadamayaPipeline': 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/laJornadaMaya_deprecated/laJornadaMaya/spiders/__init__.py deleted 100644 → 0
View file @ 15cbb498
# 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/laJornadaMaya_deprecated/laJornadaMaya/spiders/noticias.py deleted 100644 → 0
View file @ 15cbb498
import scrapy, json, re
from datetime import datetime, date, timedelta, tzinfo
"""
Esta version descarga ingresando una fecha.
USO:
scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
No es recomendable para fechas de mas de un mes de antiguas.
"""
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
class UTC(tzinfo):
"""clase para el 'time zone' (zona horaria)"""
def utcoffset(self, dt):
# zona horaria para yucatan (centro de mexico): utc-6
return timedelta(hours=-6)
def tzname(self, dt):
# nombre de la zona horaria
return 'UTC-6'
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.found = False
# self.flag = False
self.tz = UTC()
self.year = getattr(self, 'year', None)
self.month = getattr(self, 'month', None)
self.day = getattr(self, 'day', None)
self.req_date = date(int(self.year), int(self.month), int(self.day))
self.date_format = "%Y-%m-%d"
self.baseURL = 'https://www.lajornadamaya.mx'
section_list = ['yucatan', 'quintana-roo', 'campeche', 'deportes', 'nacional',
'internacional', 'opinion']
# section_list = ['deportes']
for section in section_list:
self.section = section
for count in range(0,2):
if ( count == 0 ):
yield scrapy.Request(url=self.baseURL+'/'+section, callback=self.parse_2)
elif (count == 1):
# self.section = section
self.page = 0
self.flag = False
self.found = False
page = -1
if not ( section == 'opinion' ):
while True:
if ( self.flag ):
self.flag = False
break
page+=1
yield scrapy.Request(url=self.baseURL+'/'+section+'?p='+str(page), callback=self.parse)
if ( self.found ):
self.found = False
self.page -= 1
if ( self.page > 0 ):
self.page -= 1
for pag in range(self.page, self.page+6):
yield scrapy.Request(url=self.baseURL+'/'+section+'?p='+str(pag), callback=self.parse_page, dont_filter=True)
else:
yield scrapy.Request(url=self.baseURL+'/notas?opinion', callback=self.parse_page)
def parse_2(self, response): # para las primeras noticias
path_list = ['//h1[@class="title"]/a/@href', '//h2[@class="title"]/a/@href']
link_list = []
for path in path_list:
link_list += response.xpath(path).extract()
for link in link_list:
if ( link[:link.rfind('/')] == self.year+'-'+self.month.zfill(2)+'-'+self.day.zfill(2) ):
item = NoticiasItem()
d = link[:link.rfind('/')]
if len(d) == 10:
d = map(int, d.split('-'))
d = datetime(d[0], d[1], d[2], tzinfo=self.tz).isoformat('T')
elif len(d) == 19:
d, t = d.split(' ')
d = map(int, d.split('-'))
t = map(int, t.split(':'))
d = datetime(d[0],d[1],d[2],t[0],t[1],t[2],tzinfo=self.tz).isoformat('T')
item['date'] = d
item['topic'] = response.url[response.url.rfind('/')+1:].title()
# yield scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_item_2)
request = scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_item_2)
request.meta['item'] = item
yield request
def parse(self, response): # para los json
json_response = json.loads(response.text)
if not ( response.url[response.url.rfind('/')+1:] == 'notas?opinion' ):
json_list = json_response
else:
json_list = json_response['articles']
for line in json_list:
this_date = datetime.strptime(line['publishDate'][:line['publishDate'].rfind(' ')], self.date_format)
this_date = this_date.date()
if ( this_date == self.req_date ):
self.page = int(response.url[response.url.rfind('=')+1:])
self.found = True
self.flag = True
break
elif ( this_date < self.req_date ):
self.flag = True
break
def parse_item_2(self, response): # para las primeras noticias
item = response.meta['item']
# item = NoticiasItem()
text = ''
# item['date'] = response.url[:response.url.rfind('/')][response.url[:response.url.rfind('/')].rfind('/')+1:]
# item['topic'] = self.section.title()
item['title'] = response.xpath('//article/h1/text()').extract_first()
for paragraph in response.xpath('//*[@class="txt"]').extract():
text += remove_tags(paragraph) + '\n'
item['text'] = text
item['url'] = response.url
print item['title']
yield item
def parse_page(self, response): # para los json
json_response = json.loads(response.text)
if not ( response.url[response.url.rfind('/')+1:] == 'notas?opinion' ):
topic = response.url[response.url.rfind('/')+1:response.url.rfind('=')-2].title()
json_list = json_response
else:
json_list = json_response['articles']
topic = 'Opinion'
for line in json_list:
this_date = datetime.strptime(line['publishDate'][:line['publishDate'].rfind(' ')], self.date_format)
this_date = this_date.date()
if ( this_date == self.req_date ):
item = NoticiasItem()
# item['date'] = line['publishDate']
d = line['publishDate']
if len(d) == 10:
d = map(int, d.split('-'))
d = datetime(d[0], d[1], d[2], tzinfo=self.tz).isoformat('T')
elif len(d) == 19:
d, t = d.split(' ')
d = map(int, d.split('-'))
t = map(int, t.split(':'))
d = datetime(d[0],d[1],d[2],t[0],t[1],t[2],tzinfo=self.tz).isoformat('T')
item['date'] = d
item['topic'] = topic
item['title'] = line['name']
if not ( response.url[response.url.rfind('/')+1:] == 'notas?opinion' ):
request = scrapy.Request(url=self.baseURL+line['url'], callback=self.parse_item)
else:
request = scrapy.Request(url=self.baseURL+'/'+line['publishDate'][:line['publishDate'].rfind(' ')]+'/'+line['uriComponent'], callback=self.parse_item)
request.meta['item'] = item
yield request
def parse_item(self, response): # para los json
item = response.meta['item']
text = ''
for paragraph in response.xpath('//*[@class="txt"]').extract():
text += remove_tags(paragraph) + '\n'
item['text'] = text
item['url'] = response.url
print item['title']
yield item
descarga_hacia_atras/laJornadaMaya_deprecated/scrapy.cfg deleted 100644 → 0
View file @ 15cbb498
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = laJornadaMaya.settings
[deploy]
#url = http://localhost:6800/
project = laJornadaMaya
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