Skip to content

crawlersNoticias
crawlersNoticias
Commit 0ff76f58 authored by Renán Sosa Guillen's avatar Renán Sosa Guillen
Browse files
Options

deleted

parent 093e0e82
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 1351 deletions
descarga_hacia_atras/laJornadaMaya2/laJornadaMaya2/items.py deleted 100644 → 0
View file @ 093e0e82
# -*- 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 @ 093e0e82
# -*- 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 @ 093e0e82
# -*- 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 @ 093e0e82
# -*- 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 @ 093e0e82
# 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 @ 093e0e82
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 @ 093e0e82
# 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 @ 093e0e82
# -*- 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 @ 093e0e82
# -*- 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 @ 093e0e82
# -*- 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 @ 093e0e82
# -*- 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 @ 093e0e82
# 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 @ 093e0e82
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 @ 093e0e82
# 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
descarga_por_mes/proceso_prueba/proceso_prueba/items.py deleted 100644 → 0
View file @ 093e0e82
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# https://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_por_mes/proceso_prueba/proceso_prueba/middlewares.py deleted 100644 → 0
View file @ 093e0e82
# -*- 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 ProcesoPruebaSpiderMiddleware(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 ProcesoPruebaDownloaderMiddleware(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)
descarga_por_mes/proceso_prueba/proceso_prueba/pipelines.py deleted 100644 → 0
View file @ 093e0e82
# -*- 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
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_por_mes/proceso_prueba/proceso_prueba/settings.py deleted 100644 → 0
View file @ 093e0e82
# -*- coding: utf-8 -*-
# Scrapy settings for proceso_prueba 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 = 'proceso_prueba'
SPIDER_MODULES = ['proceso_prueba.spiders']
NEWSPIDER_MODULE = 'proceso_prueba.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'
# 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 https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 1
# 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 = True
COOKIES_DEBUG = True
SPLASH_COOKIES_DEBUG = True
# 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 = {
# 'proceso_prueba.middlewares.ProcesoPruebaSpiderMiddleware': 543,
'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
'scrapy_splash.SplashCookiesMiddleware': 723,
'scrapy_splash.SplashMiddleware': 725,
'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
# 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 = {
'proceso_prueba.pipelines.JsonWriterPipeline': 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'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
SPLASH_URL = 'http://localhost:8050/'
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
descarga_por_mes/proceso_prueba/proceso_prueba/spiders/__init__.py deleted 100644 → 0
View file @ 093e0e82
# 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_por_mes/proceso_prueba/proceso_prueba/spiders/noticias.py deleted 100644 → 0
View file @ 093e0e82
# -*- coding: utf-8 -*-
"""
MEDIA:
Proceso, CDMX
USAGE:
## For this crawler 'scrapy-splash' is used because the content is loaded through javascript. ##
## Read especs_sitio_proceso.txt file. ##
$ cd proceso_prueba/
------------------------------------------------------------------------------------------------------------
## Get all the news from the most current to the oldest. It's necessary to use the parse_date_files.py file
for the news contained in noticias.json being splitted into files by date. ##
$ scrapy crawl noticias --nolog -s filename=noticias.json
------------------------------------------------------------------------------------------------------------
## Get all the news from the most current to a specific year-month date. ##
$ scrapy crawl noticias --nolog -s filename=2018-09.json -a year=2018 -a month=9
"""
import scrapy, re, cfscrape
from proceso_prueba.items import NoticiasItem
from datetime import datetime, date, timedelta, tzinfo
from scrapy.http.cookies import CookieJar
from scrapy_splash import SplashRequest, SplashFormRequest
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
class UTC(tzinfo):
"""
Class for Time Zone
"""
def utcoffset(self, dt):
## Time zone for CDMX: UTC-6 ##
return timedelta(hours=-6)
def tzname(self, dt):
## Time zone name ##
return 'UTC-6'
USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'
script = """
function main(splash)
splash:init_cookies(splash.args.cookies)
assert(splash:go{
splash.args.url,
headers=splash.args.headers,
http_method=splash.args.http_method,
body=splash.args.body,
})
assert(splash:wait(0.5))
local entries = splash:history()
local last_response = entries[#entries].response
return {
url = splash:url(),
headers = last_response.headers,
http_status = last_response.status,
cookies = splash:get_cookies(),
html = splash:html(),
}
end
"""
class QuotesSpider(scrapy.Spider):
"""
Basic Scrapy Spider class
"""
name = "noticias"
def start_requests(self):
self.tz = UTC()
year = getattr(self, 'year', None)
month = getattr(self, 'month', None)
self.month_parser = {
'enero' : '01', 'febrero' : '02', 'marzo' : '03', 'abril' : '04',
'mayo' : '05', 'junio' : '06', 'julio' : '07', 'agosto' : '08',
'septiembre' : '09', 'octubre' : '10', 'noviembre' : '11', 'diciembre' : '12'
}
self.baseURL = "https://hemeroteca.proceso.com.mx/"
login_url = "https://hemeroteca.proceso.com.mx/wp-login.php"
if year is not None and month is not None:
self.stop_date = date(int(year), int(month), 15)
# yield scrapy.Request(url=login_url, callback=self.parse_with_stop_date)
else:
self.stop_date = None
# yield scrapy.Request(url=login_url, callback=self.parse)
self.token, self.agent = cfscrape.get_tokens(login_url, user_agent=USER_AGENT)
print "token"
print self.token
yield SplashRequest(url=login_url, callback=self.parse_login, endpoint='render.html', args={ 'wait': 0.5 }, cookies=self.token,
headers={'User-Agent' : self.agent})
def parse_login(self, response):
return SplashFormRequest.from_response(
response,
method="POST",
formdata = {
'log' : 'carlos_silvaforne@yahoo.com.mx',
'pwd' : 'carlos_silvaforne@'
},
callback = self.after_login,
dont_click = True
)
def after_login(self, response):
print "\nresponse.request.headers"
print response.request.meta
print "\nresponse.headers"
print response.headers
session_legend = response.css('div.topnav > a').extract()[-1]
if session_legend is not None :
print "\nsession_legend"
print remove_tags(session_legend)
else :
print "No log in."
item_link = "https://hemeroteca.proceso.com.mx/?page_id=420325"
yield SplashRequest(url=item_link, callback=self.parse_links,
meta=response.request.meta,
endpoint='execute',
cache_args=['lua_source'],
args={'lua_source': script},
headers={'User-Agent': self.agent}
)
# yield SplashRequest(url=item_link, callback=self.parse_links, endpoint='render.html', args={ 'wait': 0.5 }, cookies=self.token,
# headers={'User-Agent' : self.agent})
def parse_links(self, response):
session_legend = response.css('div.topnav > a').extract()
print "\nresponse.body"
print response.body
# if session_legend is not None :
# print "\nsession_legend"
# print remove_tags(session_legend)
# else :
# print "No log in."
print "\nresponse.request.headers"
print response.request.headers
print "\n"
def after_login_org(self, response):
## Check login succeed before going on ##
print response.headers
print "\n"
print response.real_url
print "\n"
print response.request.headers
print "\n"
cookie_list = response.request.headers.getlist('Cookie')
cfc, cfd = cookie_list[0].split(';')
cfc = cfc.strip().split('=')
cfd = cfd.strip().split('=')
cookies = [cfc[1], cfd[1]]
cookies = {cfc[0]: cfc[1], cfd[0]: cfd[1]}
session_legend = response.css('div.topnav > a').extract()[-1]
print response.css('h1.entry-title').extract_first()
print "\n"
if session_legend is not None:
session_legend = remove_tags(session_legend)
if not "Cerrar" in session_legend:
print "Login failed."
else:
print session_legend
print "\n"
token, agent = cfscrape.get_tokens(self.baseURL, user_agent=USER_AGENT)
print token
print "\n"
if self.stop_date is None:
yield scrapy.Request(url=self.baseURL, callback=self.parse)
else:
yield SplashRequest(url=self.baseURL, callback=self.parse_with_stop_date,
cookies=cookies,
endpoint='execute',
cache_args=['lua_source'],
args={'lua_source': script},
headers={'User-Agent': USER_AGENT}
)
# request = SplashRequest(url=self.baseURL, callback=self.parse_with_stop_date,
# endpoint='execute',
# cache_args=['lua_source'],
# args={'lua_source': script},
# headers={'User-Agent': USER_AGENT}
# )
# request.meta['splash']['session_id'] = cookie_list[0]
# yield request
# if "authentication failed" in response.body:
# self.logger.error("Login failed.")
# return
# else:
# # token, agent = cfscrape.get_tokens(self.baseURL, user_agent=USER_AGENT)
# if self.stop_date is None:
# yield scrapy.Request(url=self.baseURL, callback=self.parse, dont_filter=True)
# else:
# yield scrapy.Request(url=self.baseURL, callback=self.parse_with_stop_date, dont_filter=True)
# yield scrapy.Request(
# url=self.baseURL,
# callback=self.parse_with_stop_date,
# cookies=token,
# headers={'User-Agent' : agent}
# )
def parse_with_stop_date(self, response):
print "parse_with_stop_date"
print "\n"
print response.css('h1.entry-title').extract_first()
print "\n"
print response.cookiejar
print "\n"
print response.headers
print "\n"
session_legend = response.css('div.topnav > a').extract()[-1]
if session_legend is not None :
print remove_tags(session_legend)
print "\n"
else :
print "No log in."
TO_NEXT_PAGE = True
for item in response.css('div.catpor-box > div'):
item_date = item.css('span.catpor-published').extract_first()
if item_date is not None:
item_date = remove_tags(item_date).replace(",", '')
item_date = item_date.split(' ')
item_date[1] = self.month_parser[item_date[1]]
item_date = map(int, item_date)
item_date = date(item_date[2], item_date[1], item_date[0])
if item_date >= self.stop_date:
item_link = item.css('span.catpor-title > a::attr(href)').extract_first()
print item_link
# token, agent = cfscrape.get_tokens(self.baseURL, user_agent=USER_AGENT)
# yield scrapy.Request(url=item_link, callback=self.parse_links, cookies=cookies)
# yield scrapy.Request(url=item_link, callback=self.parse_links, cookies=token,
# headers={'User-Agent' : agent})
# yield SplashRequest(url=item_link, callback=self.parse_links,
# endpoint='execute',
# cache_args=['lua_source'],
# args={'lua_source': script},
# headers={'User-Agent': USER_AGENT}
# )
else:
TO_NEXT_PAGE = False
break
if TO_NEXT_PAGE:
next_page = response.css('div.page-navigation > div.nav-next > a::attr(href)').extract_first()
if next_page is not None:
# yield scrapy.Request(url=next_page, callback=self.parse_with_stop_date)
yield SplashRequest(url=next_page, callback=self.parse_with_stop_date,
endpoint='execute',
cache_args=['lua_source'],
args={'lua_source': script},
headers={'User-Agent': USER_AGENT}
)
def parse_links_org(self, response):
print "\n\n"
print response.headers
for link in response.css('div.post-container > h2 > a::attr(href)').extract():
# print link
# token, agent = cfscrape.get_tokens(self.baseURL, user_agent=USER_AGENT)
# yield SplashRequest(url=link, callback=self.parse_item, endpoint='render.html', args={ 'wait': 0.5 }, cookies=token,
# headers={'User-Agent' : agent})
yield SplashRequest(url=link, callback=self.parse_item,
endpoint='execute',
cache_args=['lua_source'],
args={'lua_source': script},
headers={'User-Agent': USER_AGENT}
)
def parse_item_org(self, response):
# if response.url == "https://hemeroteca.proceso.com.mx/?page_id=278958&a51dc26366d99bb5fa29cea4747565fec=420203":
# print response.body
item = NoticiasItem()
text = ''
news_date = response.xpath('//div[@id="primary"]').css('span.published').extract_first()
if news_date is not None:
news_date = remove_tags(news_date)
print news_date
d, t = news_date.split(' ')
d = map(int, d.split("-"))
t = map(int, t.split(":"))
news_date = datetime(d[0], d[1], d[2], t[0], t[1], t[2], tzinfo=self.tz).isoformat('T')
title = response.xpath('//div[@id="primary"]/div/h1').extract_first()
if title is not None : title = remove_tags(title)
topic = response.css('span.entry-categories').extract_first()
if topic is not None : topic = remove_tags(topic)
for paragraph in response.xpath('//div[@id="primary"]').css('div.entry-content > div').css('p').extract():
text += remove_tags(paragraph) + '\n'
## News item info ##
item['date'] = news_date
item['title'] = title
item['topic'] = topic
item['text'] = text.strip()
item['url'] = response.url
yield item
descarga_por_mes/proceso_prueba/scrapy.cfg deleted 100644 → 0
View file @ 093e0e82
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.io/en/latest/deploy.html
[settings]
default = proceso_prueba.settings
[deploy]
#url = http://localhost:6800/
project = proceso_prueba
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