crawlers

descarga_por_dia/paisHonduras/tiempoDigitalHn/scrapy.cfg

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

descarga_por_dia/paisHonduras/tiempoDigitalHn/tiempoDigitalHn/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_por_dia/paisHonduras/tiempoDigitalHn/tiempoDigitalHn/middlewares.py

+# -*- 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 TiempodigitalhnSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/paisHonduras/tiempoDigitalHn/tiempoDigitalHn/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_por_dia/paisHonduras/tiempoDigitalHn/tiempoDigitalHn/settings.py

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

descarga_por_dia/paisHonduras/tiempoDigitalHn/tiempoDigitalHn/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_por_dia/paisHonduras/tiempoDigitalHn/tiempoDigitalHn/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from tiempoDigitalHn.items import NoticiasItem
+
+"""
+MEDIO:
+Tiempo Digital, Honduras
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-23.json -a year=2018 -a month=2 -a day=23
+"""
+
+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 QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        self.baseURL = "https://tiempo.hn/" + year + "/" + month.zfill(2) + "/" + 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)
+
+        pagination = response.css('div.page-nav').xpath('./a/@href').extract()
+        if len(pagination) > 0:
+            try:
+                pagination = pagination[-2]
+            except:
+                pagination = pagination[-1]
+            pagination = pagination.strip('/')
+            pages = int(pagination[pagination.rfind('/') + 1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=self.baseURL + '/page/' + str(page + 1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for link in response.css('div.td-ss-main-content').css('div.td_module_1').xpath('./h3/a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//span[@class="td-post-date"]/time/@datetime').extract_first()
+        item['title'] = remove_tags(response.xpath('//header[@class="td-post-title"]/h1').extract_first()).strip()
+
+        try:
+            topic = response.xpath('//ul[@class="td-category"]/li').extract()[-1]
+            item['topic'] = remove_tags(topic)
+        except:
+            item['topic'] = None
+
+        author = response.xpath('//div[@class="td-post-author-name"]/a').extract_first()
+        if author is not None:
+            item['author'] = remove_tags(author)
+
+        for p in response.xpath('//div[@class="td-post-content"]').css('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

descarga_por_dia/tiempoDigital/tiempoDigital/spiders/noticias.py

@@ -57,6 +57,8 @@ class QuotesSpider(scrapy.Spider):
             topic = post.css('div.td-module-meta-info').xpath('./a').extract_first()
             if topic is not None:
                 item['topic'] = remove_tags(topic)
+            else:
+                item['topic'] = None
             author = post.css('div.td-module-meta-info').xpath('./span[@class="td-post-author-name"]/a').extract_first()
             if author is not None:
                 item['author'] = remove_tags(author)
@@ -68,7 +70,6 @@ class QuotesSpider(scrapy.Spider):
 
 
     def parse_item(self, response):
-        print response.url
         item = response.meta['item']
         text = ''