Skip to content

crawlersNoticias
crawlersNoticias
Commit e5e3edb5 authored by Mario Chirinos's avatar Mario Chirinos
Browse files
Options

noticias de la bahia

parent 3dbe6091
Hide whitespace changes
Inline Side-by-side
Showing with 137 additions and 218 deletions
spiders/daily/noticiasBahia/noticiasBahia/items.py
View file @ e5e3edb5
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
# https://docs.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()
class NoticiasbahiaItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
date = scrapy.Field()
title = scrapy.Field()
text = scrapy.Field()
location = scrapy.Field()
author = scrapy.Field()
topic = scrapy.Field()
url = scrapy.Field()
spiders/daily/noticiasBahia/noticiasBahia/middlewares.py
View file @ e5e3edb5
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
from scrapy import signals
# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
class NoticiasbahiaSpiderMiddleware(object):
class NoticiasbahiaSpiderMiddleware:
# 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.
......@@ -20,30 +21,29 @@ class NoticiasbahiaSpiderMiddleware(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.
# Must return an iterable of Request, dict or Item objects.
# Must return an iterable of Request, or item objects.
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.
# Should return either None or an iterable of Response, dict
# or Item objects.
# Should return either None or an iterable of Request 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 NoticiasbahiaSpiderMiddleware(object):
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
class NoticiasbahiaDownloaderMiddleware:
# 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)
spiders/daily/noticiasBahia/noticiasBahia/pipelines.py
View file @ e5e3edb5
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from collections import OrderedDict
class JsonWriterPipeline(object):
def __init__(self, filename):
self.filename = filename
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html
@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)
# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
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 NoticiasbahiaPipeline:
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
spiders/daily/noticiasBahia/noticiasBahia/settings.py
View file @ e5e3edb5
# -*- coding: utf-8 -*-
# Scrapy settings for noticiasBahia 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
# https://docs.scrapy.org/en/latest/topics/settings.html
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
BOT_NAME = 'noticiasBahia'
SPIDER_MODULES = ['noticiasBahia.spiders']
NEWSPIDER_MODULE = 'noticiasBahia.spiders'
FEED_EXPORT_ENCODING="utf-8"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'noticiasBahia (+http://www.yourdomain.com)'
# Obey robots.txt rules
# ROBOTSTXT_OBEY = True
ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.5
#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
#COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
......@@ -45,31 +43,31 @@ COOKIES_ENABLED = False
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'noticiasBahia.middlewares.NoticiasbahiaSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'noticiasBahia.middlewares.MyCustomDownloaderMiddleware': 543,
# 'noticiasBahia.middlewares.NoticiasbahiaDownloaderMiddleware': 543,
#}
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# See https://docs.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 = {
'noticiasBahia.pipelines.JsonWriterPipeline': 300,
}
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
# 'noticiasBahia.pipelines.NoticiasbahiaPipeline': 300,
#}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
......@@ -82,9 +80,13 @@ 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://docs.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'
# Set settings whose default value is deprecated to a future-proof value
REQUEST_FINGERPRINTER_IMPLEMENTATION = '2.7'
TWISTED_REACTOR = 'twisted.internet.asyncioreactor.AsyncioSelectorReactor'
spiders/daily/noticiasBahia/noticiasBahia/spiders/noticias.py
View file @ e5e3edb5
# -*- coding: utf-8 -*-
import scrapy, re
from noticiasBahia.items import NoticiasItem
from datetime import datetime, timedelta, tzinfo
"""
MEDIO:
Noticias de la Bahía, Nayarit
USO:
scrapy crawl noticias --nolog -s filename=2018-02-01.json -a year=2018 -a month=2 -a day=1
"""
import scrapy
import re
from noticiasBahia.items import NoticiasbahiaItem
#-------------------------------------------------------------------------------
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
# G_RE = re.compile(r' ?- ?')
# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
class UTC(tzinfo):
"""clase para el 'time zone' (zona horaria)"""
def utcoffset(self, dt):
# zona horaria para nayarit: utc-7
return timedelta(hours=-7)
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.year = getattr(self, "year", None)
self.month = getattr(self, "month", None)
self.day = getattr(self, "day", None)
self.date_parser = {"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.baseURL = "https://noticiasdelabahia.com/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
yield scrapy.Request(url=self.baseURL, callback=self.parse)
def parse(self, response):
yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
nextPage = response.xpath('//div[@class="pagination clearfix"]/a[@class="older-posts"]/@href').extract_first()
if nextPage is not None:
yield scrapy.Request(url=nextPage, callback=self.parse)
def parse_page(self, response):
for link in response.xpath('//div[@class="row default-layout"]/article/h2/a/@href').extract():
yield scrapy.Request(url=link, callback=self.parse_item)
def parse_item(self, response):
item = NoticiasItem()
text = ''
d = response.xpath('//span[@class="date"]').extract_first()
d = remove_tags(d).strip().replace(",", '').split()
try:
dat = datetime(int(d[2]), self.date_parser[d[1].lower()], int(d[0]), tzinfo=self.tz).isoformat("T")
except:
dat = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
item['date'] = dat
item['title'] = remove_tags(response.xpath('//h1[@class="title"]').extract_first()).strip()
topic = response.xpath('//div[@class="category-list"]/ul/li/a').extract_first()
if topic is not None:
item['topic'] = remove_tags(topic).strip()
author = response.xpath('//span[@class="author"]').extract_first()
if author is not None:
item['author'] = remove_tags(author).strip()
for p in response.xpath('//div[@class="post-entry"]/p').extract():
text += remove_tags(p) + "\n"
# result = LOC_RE.search(text)
# if result:
# m = result.group(0)
# location = G_RE.sub('', m).strip()
# if len(location) <= 35:
# item['location'] = location
# text = text[text.find(m)+len(m):]
# text = EM_RE.sub('', text)
# text = TW_RE.sub('', text)
# text = TW2_RE.sub('', text)
# text = TAG2_RE.sub("\n", text)
# text = TAG3_RE.sub('', text)
item['text'] = text.strip()
item['url'] = response.url
yield item
return TAG_RE.sub('', text)
class NoticiasSpider(scrapy.Spider):
name = 'noticias'
allowed_domains = ['noticiasdlb.com']
start_urls = ['http://noticiasdlb.com/']
def start_requests(self):
self.year = getattr(self, "year", None)
self.month = getattr(self, "month", None)
self.day = getattr(self, "day", None)
self.baseURL = "https://noticiasdlb.com/{0}/{1}/{2}/".format(self.year, self.month.zfill(2), self.day.zfill(2))
yield scrapy.Request(url=self.baseURL, callback=self.parse)
#-----------------------------------------------------------------------
def parse(self, response):
print(response)
for link in response.xpath('//article/h2/a/@href').extract():
yield scrapy.Request(url=link, callback=self.parse_item)
#-------------------------------------------------------------------------------
def parse_item(self, response):
# print(response.url)
item = NoticiasbahiaItem()
item["date"]=self.year+"-"+self.month.zfill(2)+"-"+self.day.zfill(2)
item["title"]=response.xpath('//meta[@property="og:title"]/@content').extract_first()
text=""
for p in response.xpath('//article/div[@class="post-entry"]//p').extract():
text += remove_tags(p) + "\n"
item["text"]=text
item['topic'] = ", ".join(response.xpath('//a[@rel="tag"]/text()').extract())
item['author'] = ""
item["url"]=response.url
item["location"]=""
print(self.allowed_domains, item["title"])
# print(item)
yield(item)
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