Skip to content

crawlersNoticias
crawlersNoticias
Commit ef14987c authored by Mario Chirinos's avatar Mario Chirinos
Browse files
Options

borken urls

parent 5d68fa75
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 1043 deletions
spiders/daily/laJornadaGro/laJornadaGro/items.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class NoticiasItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
text = scrapy.Field()
date = scrapy.Field()
location = scrapy.Field()
author = scrapy.Field()
topic = scrapy.Field()
url = scrapy.Field()
spiders/daily/laJornadaGro/laJornadaGro/middlewares.py deleted 100644 → 0
View file @ 5d68fa75
# -*- 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 LajornadagroSpiderMiddleware(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)
spiders/daily/laJornadaGro/laJornadaGro/pipelines.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from collections import OrderedDict
class JsonWriterPipeline(object):
def __init__(self, filename):
self.filename = filename
@classmethod
def from_crawler(cls, crawler):
# Here you get whatever value was passed through the "filename" command line parameter
settings = crawler.settings
filename = settings.get('filename')
# Instantiate the pipeline with the file name
return cls(filename)
def open_spider(self, spider):
self.counter = 0
self.file = open(self.filename, 'w')
self.file.write("[")
def close_spider(self, spider):
self.file.write("]")
self.file.close()
def process_item(self, item, spider):
# print("this is my item", item)
row = []
try:
row.append(("date", item['date']))
except:
pass
try:
row.append(("topic", item['topic']))
except:
pass
try:
row.append(("title", item['title']))
except:
pass
try:
row.append(("author", item['author']))
except:
pass
try:
row.append(("location", item['location']))
except:
pass
try:
row.append(("text", item['text']))
except:
pass
try:
row.append(("url", item['url']))
except:
pass
line = OrderedDict(row)
self.counter += 1
if self.counter == 1:
self.file.write(json.dumps(line))
elif self.counter > 1:
self.file.write(",\n" + json.dumps(line))
return item
spiders/daily/laJornadaGro/laJornadaGro/settings.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Scrapy settings for laJornadaGro 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 = 'laJornadaGro'
SPIDER_MODULES = ['laJornadaGro.spiders']
NEWSPIDER_MODULE = 'laJornadaGro.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'laJornadaGro (+http://www.yourdomain.com)'
# Obey robots.txt rules
# ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.5
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'laJornadaGro.middlewares.LajornadagroSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornadaGro.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 = {
'laJornadaGro.pipelines.JsonWriterPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
spiders/daily/laJornadaGro/laJornadaGro/spiders/__init__.py deleted 100644 → 0
View file @ 5d68fa75
# 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.
spiders/daily/laJornadaGro/laJornadaGro/spiders/noticias.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
import scrapy, re
from laJornadaGro.items import NoticiasItem
from datetime import datetime, timedelta, tzinfo
"""
MEDIO:
La Jornada Guerrero, Gro.
Esta version se encarga de la descarga de la nueva pagina de La Jornada Guerrero
con url: 'http://www.lajornadaguerrero.com.mx'
Esta version descarga noticias a partir del 2017.08.15
Uso:
scrapy crawl noticias --nolog -s filename=2017-09-18.json -a year=2017 -a month=9 -a day=18
"""
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 guerrero (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()
year = getattr(self, 'year', None)
month = getattr(self, 'month', None)
day = getattr(self, 'day', None)
self.parse_month = {'Ene': '01', 'Feb': '02', 'Mar': '03', 'Abr': '04', 'May': '05', 'Jun': '06',
'Jul': '07', 'Ago': '08', 'Sep': '09', 'Oct': '10', 'Nov': '11', 'Dic': '12'}
# self.baseURL = 'http://www.ljg.com.mx'
self.baseURL = "http://www.lajornadaguerrero.com.mx"
url = "/index.php?option=com_k2&view=itemlist&task=date&year="+year+"&month="+month+"&day="+day+"&Itemid=588"
yield scrapy.Request(url=self.baseURL+url, callback=self.parse)
def parse(self, response):
yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
pagination = response.xpath('//ul[@class="pagination"]/li/a/@href').extract()[:-2]
if len(pagination) > 0:
for page in range(0, len(pagination)):
yield scrapy.Request(url=self.baseURL+pagination[page], callback=self.parse_page)
def parse_page(self, response):
for li in response.xpath('//*[@class="genericItemView"]/div[@class="genericItemHeader"]/h2/a/@href').extract():
yield scrapy.Request(url=self.baseURL+li, callback=self.parse_item)
def parse_item(self, response):
item = NoticiasItem()
path_list = ['//*[@class="itemIntroText"]/p', '//*[@class="itemFullText"]/p']
text = ''
d = response.xpath('//span[@class="itemDateCreated"]/text()').extract_first()
if d is not None:
d = d.replace('\n','')
d = d.replace('\t','')
d = d.replace(',','')
m = d[:d.find(' ')]
d = d.replace(m, self.parse_month[m])
# item['date'] = datetime.strptime(d, '%m %d %Y').date()
d = map(int, d.split(' '))
item['date'] = datetime(d[2],d[0],d[1],tzinfo=self.tz).isoformat('T')
title = response.xpath('//*[@class="itemHeader"]/h2/text()').extract_first()
if title is not None:
title = title.replace('\n','')
title = title.replace('\t','')
title = title.lstrip()
title = title.rstrip()
item['title'] = title
item['topic'] = response.xpath('//*[@class="itemCategory"]/a/text()').extract_first()
for path in path_list:
for p in response.xpath(path).extract():
text += remove_tags(p)
item['text'] = text
item['url'] = response.url
# print item['url']
yield item
spiders/daily/laJornadaGro/scrapy.cfg deleted 100644 → 0
View file @ 5d68fa75
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = laJornadaGro.settings
[deploy]
#url = http://localhost:6800/
project = laJornadaGro
spiders/daily/laJornadaGroAntiguo/laJornadaGroAntiguo/items.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class NoticiasItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
text = scrapy.Field()
date = scrapy.Field()
location = scrapy.Field()
author = scrapy.Field()
topic = scrapy.Field()
url = scrapy.Field()
spiders/daily/laJornadaGroAntiguo/laJornadaGroAntiguo/middlewares.py deleted 100644 → 0
View file @ 5d68fa75
# -*- 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 LajornadagroantiguoSpiderMiddleware(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)
spiders/daily/laJornadaGroAntiguo/laJornadaGroAntiguo/pipelines.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from collections import OrderedDict
class JsonWriterPipeline(object):
def __init__(self, filename):
self.filename = filename
@classmethod
def from_crawler(cls, crawler):
# Here you get whatever value was passed through the "filename" command line parameter
settings = crawler.settings
filename = settings.get('filename')
# Instantiate the pipeline with the file name
return cls(filename)
def open_spider(self, spider):
self.counter = 0
self.file = open(self.filename, 'w')
self.file.write("[")
def close_spider(self, spider):
self.file.write("]")
self.file.close()
def process_item(self, item, spider):
# print("this is my item", item)
row = []
try:
row.append(("date", item['date']))
except:
pass
try:
row.append(("topic", item['topic']))
except:
pass
try:
row.append(("title", item['title']))
except:
pass
try:
row.append(("author", item['author']))
except:
pass
try:
row.append(("location", item['location']))
except:
pass
try:
row.append(("text", item['text']))
except:
pass
try:
row.append(("url", item['url']))
except:
pass
line = OrderedDict(row)
self.counter += 1
if self.counter == 1:
self.file.write(json.dumps(line))
elif self.counter > 1:
self.file.write(",\n" + json.dumps(line))
return item
spiders/daily/laJornadaGroAntiguo/laJornadaGroAntiguo/settings.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Scrapy settings for laJornadaGroAntiguo 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 = 'laJornadaGroAntiguo'
SPIDER_MODULES = ['laJornadaGroAntiguo.spiders']
NEWSPIDER_MODULE = 'laJornadaGroAntiguo.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'laJornadaGroAntiguo (+http://www.yourdomain.com)'
# Obey robots.txt rules
# ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.5
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'laJornadaGroAntiguo.middlewares.LajornadagroantiguoSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornadaGroAntiguo.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 = {
'laJornadaGroAntiguo.pipelines.JsonWriterPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
spiders/daily/laJornadaGroAntiguo/laJornadaGroAntiguo/spiders/__init__.py deleted 100644 → 0
View file @ 5d68fa75
# 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.
spiders/daily/laJornadaGroAntiguo/laJornadaGroAntiguo/spiders/noticias.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
import scrapy, re
from laJornadaGroAntiguo.items import NoticiasItem
"""
Esta version se encarga de la descarga de la pagina de La Jornada Guerrero
con url: 'http://www.lajornadaguerrero.com.mx/'
--> LA ESCTRUCTURA DE LA PAGINA HA CAMBIADO. VER CRAWLER laJornadaGro.
Uso:
scrapy crawl noticias --nolog -s filename=2017-03-22.json -a year=2017 -a month=3 -a day=22
"""
TAG_RE = re.compile(r'<[^>]+>')
def remove_tags(text):
return TAG_RE.sub('', text)
class QuotesSpider(scrapy.Spider):
name = "noticias"
def start_requests(self):
self.link_list = []
self.year = getattr(self, 'year', None)
self.month = getattr(self, 'month', None)
self.day = getattr(self, 'day', None)
self.baseURL='http://www.lajornadaguerrero.com.mx/'+self.year+'/'+self.month.zfill(2)+'/'+self.day.zfill(2)
urls = [
self.baseURL,
]
for url in urls:
yield scrapy.Request(url=url, callback=self.parse)
def parse(self, response):
paths = ['//div[@class="viewlet"]/h1/a/@href', '//div[@class="viewlet"]/h2/a/@href',
'//div[@class="viewlet"]/h3/a/@href', '//div[@class="viewlet image"]/h1/a/@href',
'//div[@class="viewlet image"]/h2/a/@href', '//div[@class="viewlet image"]/h3/a/@href',
'//div[@class="text_block_200"]/p/a/@href']
for path in paths:
links = response.xpath(path).extract()
if ( len(links) > 0 ):
for link in links:
if not ( link in self.link_list ):
self.link_list.append(link)
yield scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_item)
for link in response.xpath('//*[@class="text_block_200"]/h2/a/@href').extract():
yield scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_page)
def parse_page(self, response):
paths = ['//*[@id="article_list"]/h2/a/@href',
'//*[@id="article_list"]/h3/a/@href']
for path in paths:
for link in response.xpath(path).extract():
if not ( link in self.link_list ):
yield scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_item)
def parse_item(self, response):
item = NoticiasItem()
text = ''
item['date'] = self.year+'-'+self.month.zfill(2)+'-'+self.day.zfill(2)
item['title'] = response.xpath('//*[@class="documentContent"]/h1/text()').extract_first()
item['topic'] = response.xpath('//*[@id="portal-breadcrumbs"]/a[2]/text()').extract()
for paragraph in response.xpath('//*[@class="documentContent"]/p/text()').extract():
text += paragraph
item['text'] = text
item['url'] = response.url
# print item['title']
yield item
spiders/daily/laJornadaGroAntiguo/scrapy.cfg deleted 100644 → 0
View file @ 5d68fa75
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = laJornadaGroAntiguo.settings
[deploy]
#url = http://localhost:6800/
project = laJornadaGroAntiguo
spiders/daily/laJornadaVer/laJornadaVer/items.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Define here the models for your scraped items
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/items.html
import scrapy
class NoticiasItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
title = scrapy.Field()
text = scrapy.Field()
date = scrapy.Field()
location = scrapy.Field()
author = scrapy.Field()
topic = scrapy.Field()
url = scrapy.Field()
spiders/daily/laJornadaVer/laJornadaVer/middlewares.py deleted 100644 → 0
View file @ 5d68fa75
# -*- 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 LajornadaverSpiderMiddleware(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)
spiders/daily/laJornadaVer/laJornadaVer/pipelines.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
import json
from collections import OrderedDict
class JsonWriterPipeline(object):
def __init__(self, filename):
self.filename = filename
@classmethod
def from_crawler(cls, crawler):
# Here you get whatever value was passed through the "filename" command line parameter
settings = crawler.settings
filename = settings.get('filename')
# Instantiate the pipeline with the file name
return cls(filename)
def open_spider(self, spider):
self.counter = 0
self.file = open(self.filename, 'w')
self.file.write("[")
def close_spider(self, spider):
self.file.write("]")
self.file.close()
def process_item(self, item, spider):
# print("this is my item", item)
row = []
try:
row.append(("date", item['date']))
except:
pass
try:
row.append(("topic", item['topic']))
except:
pass
try:
row.append(("title", item['title']))
except:
pass
try:
row.append(("author", item['author']))
except:
pass
try:
row.append(("location", item['location']))
except:
pass
try:
row.append(("text", item['text']))
except:
pass
try:
row.append(("url", item['url']))
except:
pass
line = OrderedDict(row)
self.counter += 1
if self.counter == 1:
self.file.write(json.dumps(line))
elif self.counter > 1:
self.file.write(",\n" + json.dumps(line))
return item
spiders/daily/laJornadaVer/laJornadaVer/settings.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
# Scrapy settings for laJornadaVer 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 = 'laJornadaVer'
SPIDER_MODULES = ['laJornadaVer.spiders']
NEWSPIDER_MODULE = 'laJornadaVer.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'laJornadaVer (+http://www.yourdomain.com)'
# Obey robots.txt rules
# ROBOTSTXT_OBEY = True
# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32
# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY = 0.5
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
COOKIES_ENABLED = False
# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False
# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#}
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'laJornadaVer.middlewares.LajornadaverSpiderMiddleware': 543,
#}
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
# 'laJornadaVer.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 = {
'laJornadaVer.pipelines.JsonWriterPipeline': 300,
}
# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False
# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
spiders/daily/laJornadaVer/laJornadaVer/spiders/__init__.py deleted 100644 → 0
View file @ 5d68fa75
# 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.
spiders/daily/laJornadaVer/laJornadaVer/spiders/noticias.py deleted 100644 → 0
View file @ 5d68fa75
# -*- coding: utf-8 -*-
import scrapy, re
from laJornadaVer.items import NoticiasItem
from datetime import datetime, timedelta, tzinfo
"""
MEDIO:
La Jornada de Veracruz, Ver.
USO:
scrapy crawl noticias --nolog -s filename=2017-03-22.json -a year=2017 -a month=3 -a day=22
"""
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 veracruz (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):
tz = UTC()
year = getattr(self, 'year', None)
month = getattr(self, 'month', None)
day = getattr(self, 'day', None)
self.date = datetime(int(year), int(month), int(day), tzinfo=tz).isoformat('T')
self.baseURL = 'http://www.jornadaveracruz.com.mx/'
self.builtURL= self.baseURL+'Archive.aspx?date='+day.zfill(2)+'/'+month.zfill(2)+'/'+year
yield scrapy.Request(url=self.builtURL, callback=self.parse)
def parse(self, response):
paths = ['//*[@class="article-header"]/h2/a/@href',
'//ul[@class="article-array content-category"]/li/a/@href']
for path in paths:
links = response.xpath(path).extract()
if len(links) > 0:
for link in links:
yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item)
# for link in response.xpath('//*[@class="text_block_200"]/h2/a/@href').extract():
# yield scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_page)
def parse_page(self, response):
paths = ['//*[@id="article_list"]/h2/a/@href',
'//*[@id="article_list"]/h3/a/@href']
for path in paths:
for link in response.xpath(path).extract():
if not link in self.link_list:
yield scrapy.Request(url=self.baseURL+'/'+link, callback=self.parse_item)
def parse_item(self, response):
item = NoticiasItem()
text = ''
item['date'] = self.date
title = response.xpath('//h2[@class="article-title"]/text()').extract_first()
title = title.replace('\r','')
title = title.replace('\n','')
title = title.lstrip(' ')
title = title.rstrip(' ')
item['title'] = title
topic = response.xpath('//*[@class="content-article-title"]/h2/text()').extract_first()
topic = topic.replace('\r','')
topic = topic.replace('\n','')
topic = topic.lstrip(' ')
topic = topic.rstrip(' ')
item['topic'] = topic
# item['author'] = response.xpath('//*[@class="right-side"]/div/a[@rel="author"]/text()').extract_first()
paragraph = response.xpath('//*[@class="shortcode-content"]/p/text()').extract()
if len(paragraph) > 0:
for p in paragraph:
text += paragraph[3]
else:
for p in response.xpath('//*[@class="shortcode-content"]').extract():
text += remove_tags(p) + '\n'
item['text'] = text
item['url'] = response.url
# print item['title']
yield item
spiders/daily/laJornadaVer/scrapy.cfg deleted 100644 → 0
View file @ 5d68fa75
# Automatically created by: scrapy startproject
#
# For more information about the [deploy] section see:
# https://scrapyd.readthedocs.org/en/latest/deploy.html
[settings]
default = laJornadaVer.settings
[deploy]
#url = http://localhost:6800/
project = laJornadaVer
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