Skip to content

crawlersNoticias
crawlersNoticias
Commit bddd5804 authored by Renán Sosa Guillen's avatar Renán Sosa Guillen
Browse files
Options

crawlers

parent 620c10e0
Hide whitespace changes
Inline Side-by-side
Showing with 845 additions and 835 deletions
descarga_hacia_atras/laJornadaBC/laJornadaBC/items.py
View file @ bddd5804
......@@ -3,12 +3,18 @@
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
# https://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class LajornadabcItem(scrapy.Item):
class NoticiasItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
pass
title = scrapy.Field()
text = scrapy.Field()
date = scrapy.Field()
location = scrapy.Field()
author = scrapy.Field()
topic = scrapy.Field()
url = scrapy.Field()
descarga_hacia_atras/laJornadaBC/laJornadaBC/middlewares.py
View file @ bddd5804
......@@ -3,7 +3,7 @@
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
......@@ -20,14 +20,14 @@ class LajornadabcSpiderMiddleware(object):
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_spider_input(response, spider):
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(response, result, spider):
def process_spider_output(self, response, result, spider):
# Called with the results returned from the Spider, after
# it has processed the response.
......@@ -35,7 +35,7 @@ class LajornadabcSpiderMiddleware(object):
for i in result:
yield i
def process_spider_exception(response, exception, spider):
def process_spider_exception(self, response, exception, spider):
# Called when a spider or process_spider_input() method
# (from other spider middleware) raises an exception.
......@@ -43,7 +43,7 @@ class LajornadabcSpiderMiddleware(object):
# or Item objects.
pass
def process_start_requests(start_requests, spider):
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.
......@@ -54,3 +54,50 @@ class LajornadabcSpiderMiddleware(object):
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
class LajornadabcDownloaderMiddleware(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_hacia_atras/laJornadaBC/laJornadaBC/pipelines.py
View file @ bddd5804
......@@ -3,9 +3,73 @@
# 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
# 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()
class LajornadabcPipeline(object):
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/laJornadaBC/laJornadaBC/settings.py
View file @ bddd5804
......@@ -5,9 +5,9 @@
# 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
# 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 = 'laJornadaBC'
......@@ -19,21 +19,21 @@ NEWSPIDER_MODULE = 'laJornadaBC.spiders'
#USER_AGENT = 'laJornadaBC (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = True
# 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 https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
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
COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
......@@ -45,31 +45,31 @@ ROBOTSTXT_OBEY = True
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'laJornadaBC.middlewares.LajornadabcSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornadaBC.middlewares.MyCustomDownloaderMiddleware': 543,
# 'laJornadaBC.middlewares.LajornadabcDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# See https://doc.scrapy.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 = {
# 'laJornadaBC.pipelines.LajornadabcPipeline': 300,
#}
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'laJornadaBC.pipelines.JsonWriterPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
......@@ -82,7 +82,7 @@ ROBOTSTXT_OBEY = True
#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
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
......
descarga_hacia_atras/laJornadaBC/laJornadaBC/spiders/noticias.py
View file @ bddd5804
import scrapy, re
from datetime import datetime, date, timedelta
# -*- coding: utf-8 -*-
"""
Esta version descarga ingresando una fecha.
USO:
MEDIA:
La Jornada Baja California, Baja California
USAGE:
$ cd laJornadaBC/
------------------------------------------------------------------------------------------------------------
## 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 date. ##
$ scrapy crawl noticias --nolog -s filename=2017-02-21.json -a year=2017 -a month=2 -a day=21
"""
scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=2 -a day=21
import scrapy, re, json
from datetime import datetime, date
from laJornadaBC.items import NoticiasItem
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)
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 ImportantFlowData(scrapy.Item):
"""
Useful data for the flow of the implementation
"""
to_next_page = scrapy.Field()
is_last_link = scrapy.Field()
return_url = scrapy.Field()
class QuotesSpider(scrapy.Spider):
name = "noticias"
def start_requests(self):
section_list = ['baja-california', 'chihuahua', 'mexico', 'mundo',
'cultura', 'espectaculos', 'deportes']
year = getattr(self, 'year', None)
month = getattr(self, 'month', None)
day = getattr(self, 'day', None)
self.baseURL = 'http://jornadabc.mx/'
self.date = date(int(year), int(month), int(day))
self.pages = 100
for s in section_list:
yield scrapy.Request(url=self.baseURL+'seccion/'+s, callback=self.parse_pagination)
def parse_pagination(self, response):
pagination = response.xpath('//li[@class="pager-last odd last"]/a/@href').extract()
if len(pagination) > 0:
p = 1
while p <= self.pages:
if p == 1:
yield scrapy.Request(url=response.url, callback=self.parse_link, dont_filter=True)
elif p > 1:
yield scrapy.Request(url=response.url+'?page='+str(p+1), callback=self.parse_link)
p += 1
else:
yield scrapy.Request(url=response.url, callback=self.parse_link, dont_filter=True)
def parse_link(self, response):
section = response.url[response.url.rfind('/')+1:]
if section == 'espectaculos' or section == 'deportes':
path = '//*[@class="region region-soft-first"]'
else:
path = '//*[@class="region region-hard-first"]'
link_list = response.xpath(path).css('div.views-row').xpath('./*[@class="views-field views-field-title"]/span[@class="field-content"]/a/@href').extract()
if len(link_list) > 0:
for link in link_list:
news_date = datetime.strptime(link[:link.rfind('/')][link[:link.rfind('/')].rfind('/')+1:], '%d-%m-%Y').date()
if news_date == self.date:
yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item)
def parse_item(self, response):
item = NoticiasItem()
text = ''
## la fecha de la noticia 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
"""
Basic Scrapy Spider class
"""
name = "noticias"
def start_requests(self):
year = getattr(self, "year", None)
month = getattr(self, "month", None)
day = getattr(self, "day", None)
self.base_url = "http://jornadabc.mx"
section_list = ["baja-california", "chihuahua", "mexico", "mundo", "cultura", "espectaculos", "deportes"]
if year is not None and month is not None and day is not None:
self.stop_date = date(int(year), int(month), int(day))
for s in section_list:
flow_info = ImportantFlowData()
flow_info['to_next_page'] = False
request = scrapy.Request(url=self.base_url + "/seccion/" + s, callback=self.parse_with_stop_date)
request.meta['item'] = flow_info
yield request
elif year is None and month is None and day is None:
for s in section_list:
yield scrapy.Request(url=self.base_url + "/seccion/" + s, callback=self.parse)
else:
print "Unable to execute this crawler with current given parameters."
print "Enter all parameters: year, month and day, or none of them."
def parse(self, response):
link_list = response.css('div.region-hard-first').css('div.views-field-title > span > a::attr(href)').extract()
for link in link_list:
yield scrapy.Request(url=self.base_url + link, callback=self.parse_item)
next_page = response.css('li.pager-next > a::attr(href)').extract_first()
if next_page is not None:
yield scrapy.Request(url=self.base_url + next_page, callback=self.parse)
def parse_with_stop_date(self, response):
flow_info = response.meta['item']
if not flow_info['to_next_page']:
link_list = response.css('div.region-hard-first').css('div.views-field-title > span > a::attr(href)').extract()
for link in link_list:
flow_info = ImportantFlowData()
flow_info['return_url'] = response.url
if link_list.index(link) == link_list.index(link_list[-1]):
flow_info['is_last_link'] = True
else:
flow_info['is_last_link'] = False
request = scrapy.Request(url=self.base_url + link, callback=self.parse_item_with_stop_date)
request.meta['item'] = flow_info
yield request
else:
next_page = response.css('li.pager-next > a::attr(href)').extract_first()
if next_page is not None:
flow_info = ImportantFlowData()
flow_info['to_next_page'] = False
request = scrapy.Request(url=self.base_url + next_page, callback=self.parse_with_stop_date)
request.meta['item'] = flow_info
yield request
def parse_item(self, response):
item = NoticiasItem()
news_date = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
title = response.css('div.block-content > h1 > a').extract_first()
if title is not None : title = remove_tags(title)
topic = response.css('span.section').extract_first()
if topic is not None : topic = remove_tags(topic)
text = response.css('div.region-article-second').css('div.block-content').css('div.rtejustify').extract_first()
if text is not None:
text = remove_tags(text)
elif text is None or text == '':
text = ''
for p in response.css('div.region-article-second').css('div.block-content').css('div.field-items').css('p').extract():
text += remove_tags(p) + "\n"
## News item info ##
item['date'] = news_date
item['title'] = title
item['topic'] = topic
item['text'] = text.strip()
item['url'] = response.url
yield item
def parse_item_with_stop_date(self, response):
news_date = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
news_date = news_date[:news_date.find("T")]
news_date = datetime.strptime(news_date, '%Y-%m-%d').date()
if news_date >= self.stop_date:
flow_info = response.meta['item']
item = NoticiasItem()
news_date = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
title = response.css('div.block-content > h1 > a').extract_first()
if title is not None : title = remove_tags(title)
topic = response.css('span.section').extract_first()
if topic is not None : topic = remove_tags(topic)
text = response.css('div.region-article-second').css('div.block-content').css('div.rtejustify').extract_first()
if text is not None:
text = remove_tags(text)
elif text is None or text == '':
text = ''
for p in response.css('div.region-article-second').css('div.block-content').css('div.field-items').css('p').extract():
text += remove_tags(p) + "\n"
## News item info ##
item['date'] = news_date
item['title'] = title
item['topic'] = topic
item['text'] = text.strip()
item['url'] = response.url
yield item
if flow_info['is_last_link']:
flow_info['to_next_page'] = True
request = scrapy.Request(url=flow_info['return_url'], callback=self.parse_with_stop_date, dont_filter=True)
request.meta['item'] = flow_info
yield request
descarga_hacia_atras/laJornadaBC/scrapy.cfg
View file @ bddd5804
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
# https://scrapyd.readthedocs.io/en/latest/deploy.html
[settings]
default = laJornadaBC.settings
......
descarga_por_dia/expresoChiapas/expresoChiapas/spiders/noticias.py
View file @ bddd5804
# -*- coding: utf-8 -*-
"""
===========================================================================
THIS VERSION OF Expreso Chiapas IS NOW DEPRECATED SINCE THE SITE'S WEB PAGE
NO LONGER ALLOWS ACCES BY DAY.
THE NEW VERSION CAN BE FOUNd IN THE descarga_hacia_atras FOLDER.
===========================================================================
"""
"""
MEDIA:
Expreso Chiapas, Chiapas
......@@ -31,20 +19,7 @@ TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
CLEAN_RE = re.compile(r'\A.*?\sl\s')
class UTC(tzinfo):
"""
Class for Time Zone
"""
def utcoffset(self, dt):
## Time zone for Chiapas: UTC-6 ##
return timedelta(hours=-6)
def tzname(self, dt):
## Time zone name ##
return 'UTC-6'
# CLEAN_RE = re.compile(r'\A.*?\sl\s')
......@@ -56,24 +31,23 @@ class QuotesSpider(scrapy.Spider):
def start_requests(self):
self.tz = UTC()
self.year = getattr(self, "year", None)
self.month = getattr(self, "month", None)
self.day = getattr(self, "day", None)
year = getattr(self, "year", None)
month = getattr(self, "month", None)
day = getattr(self, "day", None)
self.baseURL = "http://expresochiapas.com/noticias/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
baseURL = "http://expresochiapas.com/noticias/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
yield scrapy.Request(url=self.baseURL, callback=self.parse)
yield scrapy.Request(url=baseURL, callback=self.parse)
def parse(self, response):
for link in response.xpath('//div[@class="mag-box-container"]/ul/li/a/@href').extract():
for link in response.css('div.penci-archive__list_posts').css('h2.entry-title > a::attr(href)').extract():
yield scrapy.Request(url=link, callback=self.parse_item)
nextPage = response.xpath('//div[@class="pages-nav"]/div').css('span.last-page').xpath('./a/@href').extract_first()
if nextPage is not None and nextPage != '':
yield scrapy.Request(url=nextPage, callback=self.parse)
next_page = response.css('div.nav-links').css('a.next::attr(href)').extract_first()
if next_page is not None:
yield scrapy.Request(url=next_page, callback=self.parse)
......@@ -81,28 +55,24 @@ class QuotesSpider(scrapy.Spider):
item = NoticiasItem()
text = ''
try:
## this date includes time zone ##
res = response.xpath('//article[@id="the-post"]/script[@type="application/ld+json"]').extract_first()
if res is not None:
res = remove_tags(res)
jsonObj = json.loads(res)
dat = jsonObj['datePublished']
except:
dat = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
item['date'] = dat
news_date = response.css('time.entry-date::attr(datetime)').extract_first()
item['title'] = remove_tags(response.xpath('//div[@class="entry-header"]/h1').extract_first()).strip()
title = response.css('h1.entry-title').extract_first()
if title is not None: title = remove_tags(title)
topic = response.xpath('//div[@class="entry-header"]/h5/a').extract_first()
if topic is not None:
item['topic'] = remove_tags(topic)
topic = response.css('div.penci-entry-categories').css('a').extract_first()
if topic is not None: topic = remove_tags(topic)
for p in response.xpath('//div[@class="entry-content entry clearfix"]/p').extract():
for p in response.css('div.penci-entry-content > p').extract():
p = p.replace("<br>", "\n")
text += remove_tags(p) + "\n"
text = text.strip()
item['text'] = CLEAN_RE.sub('', text)
item['url'] = response.url
## 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_dia/laJornada/laJornada/items.py
View file @ bddd5804
......@@ -3,7 +3,7 @@
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
# https://doc.scrapy.org/en/latest/topics/items.html
import scrapy
......
descarga_por_dia/laJornada/laJornada/middlewares.py
View file @ bddd5804
......@@ -3,7 +3,7 @@
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
......@@ -20,14 +20,14 @@ class LajornadaSpiderMiddleware(object):
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_spider_input(response, spider):
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(response, result, spider):
def process_spider_output(self, response, result, spider):
# Called with the results returned from the Spider, after
# it has processed the response.
......@@ -35,7 +35,7 @@ class LajornadaSpiderMiddleware(object):
for i in result:
yield i
def process_spider_exception(response, exception, spider):
def process_spider_exception(self, response, exception, spider):
# Called when a spider or process_spider_input() method
# (from other spider middleware) raises an exception.
......@@ -43,7 +43,7 @@ class LajornadaSpiderMiddleware(object):
# or Item objects.
pass
def process_start_requests(start_requests, spider):
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.
......@@ -54,3 +54,50 @@ class LajornadaSpiderMiddleware(object):
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
class LajornadaDownloaderMiddleware(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_dia/laJornada/laJornada/pipelines.py
View file @ bddd5804
......@@ -3,7 +3,7 @@
# 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
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from collections import OrderedDict
......
descarga_por_dia/laJornada/laJornada/settings.py
View file @ bddd5804
......@@ -5,9 +5,9 @@
# 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
# 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 = 'laJornada'
......@@ -25,7 +25,7 @@ NEWSPIDER_MODULE = 'laJornada.spiders'
#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 https://doc.scrapy.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:
......@@ -45,31 +45,31 @@ COOKIES_ENABLED = False
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
# SPIDER_MIDDLEWARES = {
# 'laJornada.middlewares.LajornadaSpiderMiddleware': 543,
#}
# }
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornada.middlewares.MyCustomDownloaderMiddleware': 543,
#}
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
# 'laJornada.middlewares.LajornadaDownloaderMiddleware': 543,
# }
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# See https://doc.scrapy.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
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'laJornada.pipelines.JsonWriterPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
......@@ -82,7 +82,7 @@ ITEM_PIPELINES = {
#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
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
......
descarga_por_dia/laJornada/laJornada/spiders/noticias.py
View file @ bddd5804
# -*- coding: utf-8 -*-
"""
=======================================================================
THIS VERSION OF La Jornada IS NOW DEPRECATED SINCE THE SITE'S WEB PAGE
NO LONGER ALLOWS ACCES BY DAY.
THE NEW VERSION CAN BE FOUND IN THE descarga_por_rss FOLDER.
=======================================================================
MEDIA:
La Jornada, CDMX
USAGE:
## Get all the news from a specific date. ##
---------------------------------------------------------------------------------------------
$ cd laJornada/
$ scrapy crawl noticias --nolog -s filename=2017-03-22.json -a year=2017 -a month=3 -a day=22
"""
"""
MEDIO:
La Jornada, CDMX
USO:
scrapy crawl noticias --nolog -s filename=2017-03-22.json -a year=2017 -a month=3 -a day=22
"""
import scrapy, re
import scrapy, re, json
from laJornada.items import NoticiasItem
from datetime import date, datetime, timedelta, tzinfo, time
from collections import OrderedDict
from datetime import datetime, timedelta, tzinfo
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
# re: r'(Twitter:\s+)?(@[\w.%+-]+.)?'
TW_RE = re.compile(r"""
(Twitter: # inicio de bloque, contiene la cadena 'Twitter:' (case insensitive)
\s+ # cualquier espacio (\t\n\r\f), una o mas ocurrencias
)? # fin de bloque, ninguna o una ocurrencia del bloque
(@ # inicio de bloque, contiene caracter '@'
[\w.%+-]+ # cualquier caracter alfanumerico mas los signos (.%+-), una o mas ocurrencias
. # cualquier caracter, excepto '\n'
)? # fin de bloque, ninguna o una ocurrencia del bloque
""", re.X|re.I) # banderas: verbose|case insensitive
# re: r'(Facebook|Vk):\s+[\w.%+-]+.'
FB_RE = re.compile(r"""
(Facebook|Vk) # bloque, contiene la cadena 'Facebook' o 'Vk' (case insensitive)
: # contiene el caracter ':'
\s+ # cualquier espacio (\t\n\r\f), una o mas ocurrencias
[\w.%+-]+ # cualquier caracter alfanumerico mas los signos (.%+-), una o mas ocurrencias
. # cualquier caracter, excepto '\n'
""", re.X|re.I) # banderas: verbose|case insensitive
# re: r'\(?(Foro:\s+)?(https?:\/\/)?([w{3}.])?[\w%+-]+(\.[a-zA-Z]{2,6}){1,2}[/\w.#$%&+-]*\)?.'
URL_RE = re.compile(r"""
\(? # contiene o no caracter '(', ninguna o una vez
(Foro: # inicio de bloque, contiene la cadena 'Foro:' (case insensitive)
\s+ # cualquier espacio (\t\n\r\f), una o mas ocurrencias
)? # fin de bloque, ninguna o una ocurrencia del bloque
(http # inicio de bloque, contiene cadena 'http'
s? # contiene o no caracter 's'
:\/\/ # contiene cadena '://'
)? # fin de bloque, ninguna o una ocurrencia del bloque
([w{3}.])? # el caracter 'w' tres veces y/o punto (www.), ninguna o una vez
[\w%+-]+ # cualquier caracter alfanumerico mas los signos (%+-), una o mas ocurrencias
(\. # inicio de bloque, contiene caracter '.'
[a-zA-Z]{2,6} # 2 a 6 letras, minusculas o mayusculas
){1,2} # fin de bloque, bloque se repite de 1 a 2 veces
[/\w.#$%&+-]* # seguido de '/', cualquier caracter alfanumerico mas los signos (.#$%&+-), cero o mas ocurrencias
\)? # contiene o no caracter ')', ninguna o una vez
. # cualquier caracter, excepto '\n'
""", re.X|re.I) # banderas: verbose|case insensitive
# re: r'[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?'
EMAIL_RE = re.compile(r"""
[\w.-]+ # cualquier caracter alfanumerico mas los signos (.-), una o mas repeticiones
@ # seguido de '@'
[\w-]+ # cualquier caracter alfanumerico mas el signo '-', una o mas repeticiones
(\. # inicio de bloque, contiene '.'
[a-zA-Z]{2,6} # 2 a 6 letras, minusculas o mayusculas
){1,2} # fin de bloque, bloque se repite de 1 a 2 veces
\s? # cualquier espacio (\t\n\r\f), ninguna o una coincidencia
""", re.X|re.I) # banderas: verbose|case insensitive
DIVP_RE = re.compile(r'(<div class="(credito-(autor|titulo)|hemero)">.*?<\/div>|<p class="s-s">.{,35}<\/p>|<span class="loc">.*?<\/span>)', re.S)
TRANSLATION_RE = re.compile(r'Traducci.n.*', re.I|re.S)
def clean_raw(rawText):
text = rawText.replace("* * *", '')
text = DIVP_RE.sub('', text)
text = TRANSLATION_RE.sub('', text)
return text
def text_cleaning(text):
"""
Function for cleaning news text
"""
"""
Elimina los espacios dobles, triples o mayores, innecesarios dentro del texto. Primero divide el texto de
acuerdo a los saltos de linea, despues divide cada segmento en palabras sin tomar en cuenta espacios. Luego
las palabras son agrupadas en nuevos segmentos con un solo espacio entre ellas y se agregan los saltos de
linea necesarios.
"""
newText = ''
counter = 0
text = text.replace(u'\u0164', '')
text = text.replace("Afp", '')
for segment in text.split("\n"):
counter += 1
if counter == 1:
newText += " ".join(segment.split())
elif counter > 1:
newText += "\n" + " ".join(segment.split())
"""---------------------------------------------------------------------------------------------------"""
class QuotesSpider(scrapy.Spider):
"""
Elimina del texto la info de facebook, twitter, foro y correo electronico.
Basic Scrapy Spider class
"""
newText = TW_RE.sub('', newText)
newText = FB_RE.sub('', newText)
newText = EMAIL_RE.sub('', newText)
newText = URL_RE.sub('', newText)
newText = TRANSLATION_RE.sub('', newText)
"""---------------------------------------------------------------------------------------------------"""
return newText
class UTC(tzinfo):
"""clase para el 'time zone' (zona horaria)"""
def utcoffset(self, dt):
# zona horaria para centro de mexico: utc-6
return timedelta(hours=-6)
def tzname(self, dt):
# nombre de la zona horaria
return 'UTC-6'
class QuotesSpider(scrapy.Spider):
name = "noticias"
def start_requests(self):
self.tz = UTC()
self.counter = 0
year = getattr(self, 'year', None)
month = getattr(self, 'month', None)
day = getattr(self, 'day', None)
self.baseURL='http://www.jornada.unam.mx/'+year+'/'+month.zfill(2)+'/'+day.zfill(2)+'/'
self.comparison_date_1 = date(2001, 12, 7)
self.comparison_date_2 = date(2002, 1, 8)
self.comparison_date_3 = date(2003, 4, 25)
self.comparison_date_4 = date(2004, 11, 16)
self.comparison_date_5 = date(2004, 12, 12)
self.comparison_date_6 = date(2005, 1, 31)
self.comparison_date_7 = date(2009, 2, 15)
self.date = date(int(year), int(month), int(day))
self.parse_month = {'enero': 1, 'febrero': 2, 'marzo': 3, 'abril': 4,
'mayo': 5, 'junio': 6, 'julio': 7, 'agosto': 8,
'septiembre': 9, 'octubre': 10, 'noviembre': 11, 'diciembre': 12}
# self.section_list = ['opinion', 'politica', 'economia', 'mundo', 'estados', 'ciencias',
# 'capital', 'sociedad', 'cultura', 'espectaculos', 'deportes']
# for section in section_list:
# para la fecha 2009/02/15 o menores, se tiene una estructura determinada de pagina
# para las fechas mayores a esa la estructura cambia
# if ( requested_date <= comparison_date_1 ):
# yield scrapy.Request(url=self.baseURL+section, callback=self.parse)
# else:
# yield scrapy.Request(url=self.baseURL+section, callback=self.parse_2)
if self.date <= self.comparison_date_2:
section_list = ['index.html', 'edito.html', 'opinion.html', 'politica.html',
'economia.html', 'cultura.html', 'espectaculos.html', 'estados.html',
'capital.html', 'mundo.html', 'soc-jus.html', 'deportes.html']
parse_s = {'index.html': 'Portada', 'edito.html': 'Editorial', 'opinion.html': 'Opinion',
'politica.html': 'Politica', 'economia.html': 'Economia',
'cultura.html': 'Cultura', 'espectaculos.html': 'Espectaculos', 'estados.html': 'Estados',
'capital.html': 'Capital', 'mundo.html': 'Mundo', 'soc-jus.html': 'Sociedad',
'deportes.html': 'Deportes'}
for s in section_list:
item = NoticiasItem()
# item['date'] = self.date
item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
item['topic'] = parse_s[s]
if s == 'edito.html':
request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item)
else:
request = scrapy.Request(url=self.baseURL+s, callback=self.parse)
request.meta['item'] = item
yield request
elif self.date > self.comparison_date_2 and self.date <= self.comparison_date_3:
section_list = ['index.html', 'edito.html', 'opinion.html', 'politica.html',
'economia.html', 'cultura.html', 'espectaculos.html', 'estados.html',
'capital.html', 'mundo.html', 'soc-jus.html', 'deportes.html',
'index.php', 'edito.php', 'opinion.php', 'politica.php',
'economia.php', 'cultura.php', 'espectaculos.php', 'estados.php',
'capital.php', 'mundo.php', 'soc-jus.php', 'deportes.php']
parse_s = {'index.html': 'Portada', 'edito.html': 'Editorial', 'opinion.html': 'Opinion',
'politica.html': 'Politica', 'economia.html': 'Economia',
'cultura.html': 'Cultura', 'espectaculos.html': 'Espectaculos', 'estados.html': 'Estados',
'capital.html': 'Capital', 'mundo.html': 'Mundo', 'soc-jus.html': 'Sociedad',
'deportes.html': 'Deportes',
'index.php': 'Portada', 'edito.php': 'Editorial', 'opinion.php': 'Opinion',
'politica.php': 'Politica', 'economia.php': 'Economia',
'cultura.php': 'Cultura', 'espectaculos.php': 'Espectaculos', 'estados.php': 'Estados',
'capital.php': 'Capital', 'mundo.php': 'Mundo', 'soc-jus.php': 'Sociedad',
'deportes.php': 'Deportes'}
for s in section_list:
item = NoticiasItem()
# item['date'] = self.date
item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
item['topic'] = parse_s[s]
if s == 'edito.html' or s == 'correo.html' or s == 'edito.php' or s == 'correo.php':
request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item)
else:
request = scrapy.Request(url=self.baseURL+s, callback=self.parse_2)
request.meta['item'] = item
yield request
elif self.date > self.comparison_date_3 and self.date <= self.comparison_date_6:
section_list = ['indexfla.php', 'edito.php', 'opinion.php', 'correo.php', 'politica.php',
'economia.php', 'cultura.php', 'espectaculos.php', 'estados.php',
'capital.php', 'mundo.php', 'soc-jus.php', 'deportes.php', 'index.php']
parse_s = {'indexfla.php': 'Portada', 'edito.php': 'Editorial', 'opinion.php': 'Opinion',
'correo.php': 'Correo', 'politica.php': 'Politica', 'economia.php': 'Economia',
'cultura.php': 'Cultura', 'espectaculos.php': 'Espectaculos', 'estados.php': 'Estados',
'capital.php': 'Capital', 'mundo.php': 'Mundo', 'soc-jus.php': 'Sociedad',
'deportes.php': 'Deportes','index.php': 'Portada'}
for s in section_list:
item = NoticiasItem()
# item['date'] = self.date
item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
item['topic'] = parse_s[s]
if s == 'edito.php' or s == 'correo.php':
if self.date > self.comparison_date_3 and self.date <= self.comparison_date_5:
request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item)
elif self.date > self.comparison_date_5 and self.date <= self.comparison_date_6:
request = scrapy.Request(url=self.baseURL+s, callback=self.parse_item_2)
def start_requests(self):
year = getattr(self, "year", None)
month = getattr(self, "month", None)
self.day = getattr(self, "day", None)
else:
request = scrapy.Request(url=self.baseURL+s, callback=self.parse_3)
self.this_date = year + "-" + month.zfill(2) + "-" + self.day.zfill(2)
request.meta['item'] = item
yield request
self.baseURL = "https://www.jornada.com.mx/" + year + "/" + month.zfill(2) + "/" + self.day.zfill(2) + "/"
elif self.date > self.comparison_date_6:
# print 'first filter'
section_list = ['opinion', 'politica', 'economia', 'mundo', 'estados', 'ciencias',
'capital', 'sociedad', 'cultura', 'espectaculos', 'deportes']
section_list = ["politica", "mundo", "capital", "cultura", "deportes",
"economia", "sociedad", "estados", "espectaculos"]
for s in section_list:
# para las fechas menores a 2009/02/15 y mayores a 2005/01/31, se tiene una estructura determinada de pagina
# para las fechas mayores a esa la estructura cambia
if self.date <= self.comparison_date_7:
yield scrapy.Request(url=self.baseURL+s, callback=self.parse_5)
elif self.date > self.comparison_date_7:
# print 'second filter in ' + self.baseURL + s
yield scrapy.Request(url=self.baseURL+s, callback=self.parse_6)
for s in section_list:
yield scrapy.Request(url=self.baseURL + s, callback=self.parse)
def parse(self, response):
item = response.meta['item']
if self.date <= self.comparison_date_1:
if item['topic'] == 'Portada':
path = '//td[@rowspan="3"]'
else:
if len(response.xpath('//td[@align="center"]').css('a::attr(href)').extract()) > 0:
path = '//td[@align="center"]'
else:
path = '//td[@align="CENTER"]'
elif self.date > self.comparison_date_1 and self.date <= self.comparison_date_2:
if item['topic'] == 'Portada':
path = '//empieza'
else:
path = '//table[@bordercolor="#CCCCCC"]'
for r in response.xpath(path).css('a::attr(href)').extract():
if r[-5:] == '.html':
request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item)
request.meta['item'] = item
yield request
def parse_2(self, response):
item = response.meta['item']
for r in response.xpath('//table[@bordercolor="#CCCCCC"]').css('a::attr(href)').extract():
if r[-5:] == '.html':
request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item)
request.meta['item'] = item
yield request
def parse_3(self, response):
item = response.meta['item']
link_list = []
link_list.extend(response.xpath('//td[@width="100%"]').css('a::attr(href)').extract())
link_list.extend(response.xpath('//td[@width="52%"]').css('a::attr(href)').extract())
link_list.extend(response.xpath('//td[@width="24%"]').css('a::attr(href)').extract())
link_list.extend(response.xpath('//td[@width="646"]').css('a::attr(href)').extract())
link_list.extend(response.xpath('//table[@width="100%"]').css('a::attr(href)').extract())
for r in link_list:
if r[-11:] == '.html&fly=1' or r[-9:] == '.php&fly=' or r[-4:] == '.php':
if self.date > self.comparison_date_3 and self.date <= self.comparison_date_6:
if self.date <= self.comparison_date_4:
request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item)
request.meta['item'] = item
yield request
elif self.date > self.comparison_date_4 and self.date <= self.comparison_date_6:
if r[:4] == 'http' and r[-4:] == '.php':
this_url = r.replace('\n','')
if self.date <= self.comparison_date_5:
request = scrapy.Request(url=this_url, callback=self.parse_item)
elif self.date > self.comparison_date_5 and self.date <= self.comparison_date_6:
request = scrapy.Request(url=this_url, callback=self.parse_item_2)
request.meta['item'] = item
yield request
# elif self.date > self.comparison_date_5 and self.date <= self.comparison_date_6:
# request = scrapy.Request(url=self.baseURL+r, callback=self.parse_item_2)
# request.meta['item'] = item
# yield request
def parse_4(self, response):
print response.url
for r in response.xpath('//td[@width="646"]').css('a::attr(href)').extract():
if r[-4:] == '.php':
print r.replace('\n','')
# request = scrapy.Request(url=r.replace('\n',''), callback=self.parse_item)
# request.meta['item'] = item
# yield request
def parse_5(self, response):
if response.url[:response.url.rfind('/')+1] == self.baseURL: # verifica que se conserva la misma URL base
section = response.url[response.url.rfind('/')+1:]
if section == 'opinion': # la seccion 'opinion' tiene una estructura diferente a las otras
path_list = ['//*[@id="columnas"]/p/a/@href',
'//*[@id="opinion"]/p/a/@href']
else:
path_list = ['//*[@id="article_list"]/h2/a/@href',
'//*[@id="article_list"]/h3/a/@href']
for path in path_list:
for link in response.xpath(path).extract():
yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item_3)
def parse_6(self, response):
if response.url[:response.url.rfind('/')+1] == self.baseURL:
# linkSet = set()
# path_list = ['//*[@class="itemfirst"]/div/a/@href', '//*[@class="item start"]/div/a/@href',
# '//*[@class="item"]/div/a/@href']
#
# for path in path_list:
# for link in response.xpath(path).extract():
# if link not in linkSet:
# linkSet.add(link)
# yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item_4)
linkSet = set()
linkLst = []
linkLst.extend(response.xpath('//*[@class="itemfirst"]/div/a/@href').extract())
linkLst.extend(response.xpath('//*[@class="item start"]/div/a/@href').extract())
linkLst.extend(response.xpath('//*[@class="item"]/div/a/@href').extract())
for l in linkLst:
link = self.baseURL + l
if not link in linkSet:
linkSet.add(link)
yield scrapy.Request(url=link, callback=self.parse_item_4)
link_set = set(response.css('div.section-cont').css('a.cabeza::attr(href)').extract())
for link in link_set:
yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
def parse_item(self, response):
"""
FECHAS <= 2004-12-12
"""
item = response.meta['item']
flag = True
text = ''
try:
title = remove_tags(response.xpath('//font[@size="5"]').extract_first())
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//p/font[@size="5"]').extract_first())
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//p/font[@size="5"]').extract()[1])
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//font[@size="4"]').extract_first())
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//p/font[@size="4"]').extract_first())
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//p/font[@size="4"][1]').extract()[1])
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//font[@size="3"]').extract_first())
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//p/font[@size="3"]').extract_first())
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//p/font[@size="3"][1]').extract()[1])
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//font[@size="+1"]').extract_first())
item['title'] = title
except:
try:
title = remove_tags(response.xpath('//font[@size="+0"]').extract_first())
item['title'] = title
except:
if self.date <= date(1999, 10, 3): # en esta fecha hay un cambio respecto a las otras en cuanto al html de la pag
try:
title = remove_tags(response.xpath('//center').extract_first())
item['title'] = title
flag = False
except:
pass
else:
pass
if flag:
if self.date <= self.comparison_date_1:
"""
FECHAS > 1999-10-03 Y FECHAS <= 2001-12-07
"""
for p in response.css('p').extract():
# text += remove_tags(p).replace('\r','') ## no toma en cuenta los primeros indices donde esta el titulo
# text = text.replace('\t','')
p = clean_raw(p)
newsText = remove_tags(p)
text += text_cleaning(newsText)
m = re.search(title, text)
if title[-1] == "?": text = text[m.end()+1:]
else: text = text[m.end():]
text = text.lstrip("\n")
text = text.rstrip("\n")
elif self.date > self.comparison_date_1 and self.date <= self.comparison_date_3:
"""
FECHAS > 2001-12-07 Y FECHAS <= 2003-04-25
"""
for p in response.xpath('//table[@bordercolor="#CCCCCC"]').css('p').extract():
# text += remove_tags(p).replace('\r','')
# text = text.replace('\t','')
p = clean_raw(p)
newsText = remove_tags(p)
text += text_cleaning(newsText)
m = re.search(title, text)
if title[-1] == "?": text = text[m.end()+1:]
else: text = text[m.end():]
text = text.lstrip("\n")
text = text.rstrip("\n")
elif self.date > self.comparison_date_3 and self.date <= self.comparison_date_4:
"""
FECHAS > 2003-04-25 Y FECHAS <= 2004-11-16
"""
p = response.css('p').extract()
for i in range(0, len(p)):
# text += remove_tags(p[i]).replace('\r','')
# text = text.replace('\t','')
aux = clean_raw(p[i])
newsText = remove_tags(aux).lstrip("\n")
newsText = newsText.rstrip("\n")
text += text_cleaning(newsText)
elif self.date > self.comparison_date_4 and self.date <= self.comparison_date_5:
"""
FECHAS > 2004-11-16 Y FECHAS <= 2004-12-12
"""
p = response.css('p').extract()
for i in range(3, len(p)):
# text += remove_tags(p[i]).replace('\r','')
# text = text.replace('\t','')
aux = clean_raw(p[i])
newsText = remove_tags(aux).lstrip("\n")
newsText = newsText.rstrip("\n")
text += text_cleaning(newsText)
if text == '':
for i in range(0, len(p)):
# text += remove_tags(p[i]).replace('\r','')
# text = text.replace('\t','')
aux = clean_raw(p[i])
newsText = remove_tags(aux).lstrip("\n")
newsText = newsText.rstrip("\n")
text += text_cleaning(newsText)
else:
"""
FECHAS <= 1999-10-03
"""
# text = remove_tags(response.body)
# text = text[len(title):]
m = re.search(title, response.body)
body = response.body[m.end():]
body = clean_raw(body)
newsText = remove_tags(body).lstrip("\n")
newsText = newsText.rstrip("\n")
text += text_cleaning(newsText)
item['text'] = text
item['url'] = response.url
yield item
def parse_item_2(self, response):
"""
FECHAS > 2004-12-12 Y FECHAS <= 2005-01-31
"""
item = response.meta['item']
text = ''
# titleLst = []
# titleLst.extend(response.xpath('//*[@id="contenido"]/h1/text()').extract())
# titleLst.extend(response.xpath('//h1/text()').extract())
titleSet = set()
titleSet.add(response.xpath('//*[@id="contenido"]/h1').extract_first())
titleSet.add(response.xpath('//h1').extract_first())
for t in titleSet:
if t is not None and t != '':
title = remove_tags(t).replace('\r','')
title = title.replace('\t','')
item['title'] = title
p = response.css('p').extract()
for i in range(4, len(p)):
# text += remove_tags(p[i]).replace('\r','')
# text = text.replace('\t','')
newsText = remove_tags(p[i]).lstrip("\n")
newsText = newsText.rstrip("\n")
text += text_cleaning(newsText)
if text == '':
for i in range(0, len(p)):
# text += remove_tags(p[i]).replace('\r','')
# text = text.replace('\t','')
newsText = remove_tags(p[i]).lstrip("\n")
newsText = newsText.rstrip("\n")
text += text_cleaning(newsText)
item['text'] = text
item['url'] = response.url
yield item
def parse_item_3(self, response):
"""
FECHAS > 2005-01-31 Y FECHAS <= 2009-02-15
"""
item = NoticiasItem()
text = ''
titleSet = set()
# item['date'] = self.date
item['date'] = datetime.combine(self.date, time()).replace(tzinfo=self.tz).isoformat('T')
# title = response.xpath('//*[@class="documentContent"]/h1[@class="title"]/text()').extract()
# if len(title) > 0:
# item['title'] = title[0]
# else:
# item['title'] = response.xpath('//*[@class="documentContent"]/h1/text()').extract_first()
titleSet.add(response.xpath('//*[@class="documentContent"]/h1[@class="title"]').extract_first())
titleSet.add(response.xpath('//*[@class="documentContent"]/h1').extract_first())
for t in titleSet:
if t is not None and t != '':
title = remove_tags(t).replace('\r','')
title = title.replace('\t','')
item['title'] = title
item['topic'] = response.xpath('//*[@id="portal-breadcrumbs"]/a[2]/text()').extract_first()
for p in response.xpath('//*[@class="documentContent"]/p').extract():
# text += remove_tags(p).replace('\r','')
# text = text.replace('\t','')
newsText = remove_tags(p).lstrip("\n")
newsText = newsText.rstrip("\n")
text += text_cleaning(newsText)
item['text'] = text
item['url'] = response.url
# print item['title']
yield item
def parse_item_4(self, response):
"""
FECHAS > 2009-02-15
"""
d = response.xpath('//*[@class="main-fecha"]/text()').extract_first()
d = d.replace('de', '').replace(' ', ' ').split(' ')
newsDate = date(int(d[3]), self.parse_month[d[2].lower()], int(d[1]))
news_date = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
d, t = news_date.split("T")
if d != self.this_date:
news_date = d[:d.rfind('-')] + "-" + self.day.zfill(2) + "T" + t
if newsDate == self.date:
item = NoticiasItem()
text = ''
# path_list = ['//*[@class="col"]/p', '//*[@class="col col1"]/p', '//*[@class="col col2"]/p']
# path_list = ['//*[@class="col"]', '//*[@class="col col1"]', '//*[@class="col col2"]']
textLst = []
textLst.extend(response.xpath('//*[@class="col"]').extract())
textLst.extend(response.xpath('//*[@class="col col1"]').extract())
textLst.extend(response.xpath('//*[@class="col col2"]').extract())
title = response.css('div.cabeza').extract_first()
if title is not None: title = remove_tags(title)
# item['date'] = self.date
item['date'] = datetime.combine(newsDate, time()).replace(tzinfo=self.tz).isoformat('T')
title = remove_tags(response.xpath('//*[@class="cabeza"]').extract_first())
item['title'] = " ".join(title.split())
item['topic'] = response.xpath('//*[@class="breadcrumb gui"]/span[2]/a/text()').extract_first()
topic = response.css('img.title::attr(title)').extract_first()
if topic is not None: topic = remove_tags(topic)
author = response.xpath('//*[@class="credito-autor"]/text()').extract_first()
if author is None or author == '':
author = response.xpath('//*[@class="credito-articulo"]/text()').extract_first()
if author is not None and author != '':
item['author'] = author
for p in response.css('div.text').css('p').extract():
p = p.replace("<br>", "\n")
text += remove_tags(p) + "\n"
location = remove_tags(response.xpath('//p[@class="s-s"]').extract_first())
if location is not None and location != '' and len(location) <= 35:
item['location'] = location
for p in textLst:
# text += remove_tags(p).replace('\r', '')
# text = text.replace('\t', '')
p = clean_raw(p)
# newsText = remove_tags(p).lstrip("\n")
# newsText = newsText.rstrip("\n")
# text += text_cleaning(newsText)
text += remove_tags(p)
text = text.lstrip("\n")
text = text.rstrip("\n")
text = text_cleaning(text)
item['text'] = text
item['url'] = response.url
# print item['title']
# print 'title: ' + item['title'] + '\nurl: ' + item['url'] + '\n'
yield item
## 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_dia/laJornada/scrapy.cfg
View file @ bddd5804
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
# https://scrapyd.readthedocs.io/en/latest/deploy.html
[settings]
default = laJornada.settings
......
descarga_por_dia/porEsto/porEsto/items.py 0 → 100644
View file @ bddd5804
# -*- 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_dia/porEsto/porEsto/middlewares.py 0 → 100644
View file @ bddd5804
# -*- 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 PorestoSpiderMiddleware(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 PorestoDownloaderMiddleware(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_dia/porEsto/porEsto/pipelines.py 0 → 100644
View file @ bddd5804
# -*- 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_dia/porEsto/porEsto/settings.py 0 → 100644
View file @ bddd5804
# -*- coding: utf-8 -*-
# Scrapy settings for porEsto 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 = 'porEsto'
SPIDER_MODULES = ['porEsto.spiders']
NEWSPIDER_MODULE = 'porEsto.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'porEsto (+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 https://doc.scrapy.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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'porEsto.middlewares.PorestoSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'porEsto.middlewares.PorestoDownloaderMiddleware': 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 = {
'porEsto.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'
descarga_por_dia/porEsto/porEsto/spiders/__init__.py 0 → 100644
View file @ bddd5804
# 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_dia/porEsto/porEsto/spiders/noticias.py 0 → 100644
View file @ bddd5804
# -*- coding: utf-8 -*-
"""
MEDIA:
Por Esto!, Yucatán
USAGE:
## Get all the news from a specific date. ##
---------------------------------------------------------------------------------------------
$ cd porEsto/
$ scrapy crawl noticias --nolog -s filename=2018-08-22.json -a year=2018 -a month=8 -a day=22
"""
import scrapy, re, json
from porEsto.items import NoticiasItem
from datetime import datetime, timedelta, tzinfo
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
class QuotesSpider(scrapy.Spider):
"""
Basic Scrapy Spider class
"""
name = "noticias"
def start_requests(self):
year = getattr(self, "year", None)
month = getattr(self, "month", None)
day = getattr(self, "day", None)
baseURL = "http://www.poresto.net/" + year + "/" + month.zfill(2) + "/" + day.zfill(2) + "/"
yield scrapy.Request(url=baseURL, callback=self.parse)
def parse(self, response):
for link in response.css('div.jeg_inner_content').css('h3.jeg_post_title > a::attr(href)').extract():
yield scrapy.Request(url=link, callback=self.parse_item)
next_page = response.css('div.jeg_navigation').css('a.next::attr(href)').extract_first()
if next_page is not None:
yield scrapy.Request(url=next_page, callback=self.parse)
def parse_item(self, response):
item = NoticiasItem()
text = ''
news_date = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
title = response.css('h1.jeg_post_title').extract_first()
if title is not None: title = remove_tags(title)
topic = response.css('div.jeg_meta_category > span > a').extract_first()
if topic is not None: topic = remove_tags(topic)
for p in response.css('div.entry-content').css('p').extract():
text += remove_tags(p) + "\n"
if text == '':
text = response.css('div.entry-content').css('div.content-inner').extract_first()
text.replace("<br>", '')
text = remove_tags(text)
## 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_dia/porEsto/scrapy.cfg 0 → 100644
View file @ bddd5804
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.io/en/latest/deploy.html
[settings]
default = porEsto.settings
[deploy]
#url = http://localhost:6800/
project = porEsto
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