merge foraneos

crawler_script/crawl_backwards.py

@@ -90,6 +90,7 @@ with open(sys.argv[1]) as data_file:
             os.chdir(mydir)
 
         os.chdir("..")
+        os.chdir("..")
 
 # print today.year
 #	scrapy crawl noticias -t json -o $y-$m-$d.json -a year=$y -a month=$m -a day=$d      # ejecucion del crawler correspondiente segun el sitio
\ No newline at end of file

descarga_hacia_atras/foraneos/heraldoHn/heraldoHn/items.py

+# -*- 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()

descarga_hacia_atras/foraneos/heraldoHn/heraldoHn/middlewares.py

+# -*- 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 HeraldohnSpiderMiddleware(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 HeraldohnDownloaderMiddleware(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/foraneos/heraldoHn/heraldoHn/pipelines.py

+# -*- 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

descarga_hacia_atras/foraneos/heraldoHn/heraldoHn/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for heraldoHn 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 = 'heraldoHn'
+
+SPIDER_MODULES = ['heraldoHn.spiders']
+NEWSPIDER_MODULE = 'heraldoHn.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'heraldoHn (+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 = {
+#    'heraldoHn.middlewares.HeraldohnSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'heraldoHn.middlewares.HeraldohnDownloaderMiddleware': 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 = {
+   'heraldoHn.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_hacia_atras/foraneos/heraldoHn/heraldoHn/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_hacia_atras/foraneos/heraldoHn/heraldoHn/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re, json
+from datetime import datetime, date
+from heraldoHn.items import NoticiasItem
+
+"""
+MEDIO:
+El Heraldo, Honduras
+USO:
+// Si se quiere obtener todas las noticias desde las más actuales hasta las más antiguas. //
+scrapy crawl noticias --nolog -s filename=noticias.json
+-------------------------------------------------------------------------------------------------
+// Si se quiere obtener todas las noticias desde las más actuales hasta una fecha específica. //
+scrapy crawl noticias --nolog -s filename=noticias.json -a year=2018 -a month=3 -a day=9
+-------------------------------------------------------------------------------------------------
+Después será necesario hacer uso del archivo parse_date_files.py para que las noticias contenidas
+en noticias.json sean separadas en archivos por fecha.
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+
+class ImportantData(scrapy.Item):
+    CONTINUE_SEARCHING = scrapy.Field()
+    LAST_LINK = scrapy.Field()
+    page = scrapy.Field()
+    section_url = scrapy.Field()
+    url = scrapy.Field()
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        if year is not None and month is not None and day is not None:
+            self.stopDate = date(int(year), int(month), int(day))
+        else:
+            self.stopDate = None
+
+        baseURL = "http://www.elheraldo.hn/"
+
+        sectionList = ["economia", "mundo", "tecnologia", "cine", "cultura", "turismo",
+                       "honduras", "sucesos", "espectaculos", "deportes"]
+        # sectionList = ["economia"]
+
+        if self.stopDate is None:
+            for s in sectionList:
+                info = ImportantData()
+                info['page'] = 1
+                request = scrapy.Request(url=baseURL + s, callback=self.parse)
+                request.meta['item'] = info
+                yield request
+
+        else:
+            for s in sectionList:
+                info = ImportantData()
+                info['page'] = 1
+                info['CONTINUE_SEARCHING'] = False
+                request = scrapy.Request(url=baseURL + s, callback=self.parse_with_stop_date)
+                request.meta['item'] = info
+                yield request
+
+
+    def parse(self, response):
+        searchData = response.meta['item']
+        CONTINUE_SEARCHING = True
+        if searchData['page'] == 1:
+            searchData['section_url'] = response.url + "/"
+            entrySet = set(response.css('article.entry').css('div.content').css('a::attr(href)').extract())
+            entrySet.remove(searchData['section_url'])
+            linkSet = set(response.css('article.grid').css('div.content').css('a::attr(href)').extract())
+            linkSet.remove(searchData['section_url'])
+            linkSet.union(entrySet)
+
+        else:
+            linkSet = set(response.css('article.grid').css('div.content').css('a::attr(href)').extract())
+            try:
+                linkSet.remove(searchData['section_url'])
+            except KeyError:
+                CONTINUE_SEARCHING = False
+
+        for link in linkSet:
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+        if CONTINUE_SEARCHING:
+            searchData['page'] += 1
+            page = searchData['page']
+            url = searchData['section_url']
+            request = scrapy.Request(url=url + "?page=" + str(page), callback=self.parse)
+            request.meta['item'] = searchData
+            yield request
+
+
+    def parse_with_stop_date(self, response):
+        searchData = response.meta['item']
+        CONTINUE_SEARCHING = searchData['CONTINUE_SEARCHING']
+
+        if not CONTINUE_SEARCHING:
+            if searchData['page'] == 1:
+                searchData['section_url'] = response.url + "/"
+                entrySet = set(response.css('article.entry').css('div.content').css('a::attr(href)').extract())
+                entrySet.remove(searchData['section_url'])
+                linkSet = set(response.css('article.grid').css('div.content').css('a::attr(href)').extract())
+                linkSet.remove(searchData['section_url'])
+                linkSet.union(entrySet)
+                linkList = list(linkSet)
+
+            else:
+                linkSet = set(response.css('article.grid').css('div.content').css('a::attr(href)').extract())
+                try:
+                    linkSet.remove(searchData['section_url'])
+                    linkList = list(linkSet)
+                except KeyError:
+                    linkList = []
+
+            for link in linkList:
+                info = ImportantData()
+                info['url'] = response.url
+                info['page'] = searchData['page']
+                info['section_url'] = searchData['section_url']
+                if link == linkList[-1]: info['LAST_LINK'] = True
+                else: info['LAST_LINK'] = False
+                reqst = scrapy.Request(url=link, callback=self.parse_item_with_stop_date)
+                reqst.meta['item'] = info
+                yield reqst
+
+        else:
+            searchData['CONTINUE_SEARCHING'] = False
+            searchData['page'] += 1
+            page = searchData['page']
+            url = searchData['section_url']
+            request = scrapy.Request(url=url + "?page=" + str(page), callback=self.parse_with_stop_date)
+            request.meta['item'] = searchData
+            yield request
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        res = remove_tags(response.xpath('//script[@type="application/ld+json"]').extract_first())
+        newsData = json.loads(res)
+
+        item['date'] = newsData['datePublished'][:-1]
+        item['title'] = newsData['headline']
+
+        try:
+            topic = newsData['articleSection']
+        except:
+            topic = None
+        item['topic'] = topic
+
+        item['text'] = newsData['articleBody']
+
+        item['url'] = response.url
+
+        yield item
+
+
+    def parse_item_with_stop_date(self, response):
+        res = remove_tags(response.xpath('//script[@type="application/ld+json"]').extract_first())
+        newsData = json.loads(res)
+        d = newsData['datePublished']
+        d = d[:d.find("T")]
+        dt = datetime.strptime(d, '%Y-%m-%d').date()
+
+        if dt >= self.stopDate:
+            info = response.meta['item']
+            item = NoticiasItem()
+            text = ''
+
+            item['date'] = newsData['datePublished'][:-1]
+            item['title'] = newsData['headline']
+
+            try:
+                topic = newsData['articleSection']
+            except:
+                topic = None
+            item['topic'] = topic
+
+            item['text'] = newsData['articleBody']
+
+            item['url'] = response.url
+
+            yield item
+
+            if info['LAST_LINK']:
+                info['CONTINUE_SEARCHING'] = True
+                request = scrapy.Request(url=info['url'], callback=self.parse_with_stop_date, dont_filter=True)
+                request.meta['item'] = info
+                yield request

descarga_hacia_atras/foraneos/heraldoHn/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = heraldoHn.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = heraldoHn