Created
January 16, 2019 01:23
-
-
Save mabelvj/631181f7716ec6d6a6756afc77882374 to your computer and use it in GitHub Desktop.
El Mundo Today Spider
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import scrapy | |
from scrapy.exceptions import CloseSpider | |
from datetime import datetime | |
from urllib.parse import urljoin | |
class EmtSpider(scrapy.Spider): | |
name = 'emt' | |
allowed_domains = ['www.elmundotoday.com'] | |
start_urls = ['https://www.elmundotoday.com/'] | |
def __init__(self, year=None, month=None, *args, **kwargs): | |
""" | |
year: int | |
If not set to any value, it ill be set to current year, | |
month: int, None (optional) | |
Search can be done within the whole year or | |
within a specific month for a year. | |
""" | |
super(EmtSpider, self).__init__(*args, **kwargs) | |
if not year: | |
year = datetime.now().year | |
self.__start_urls = [urljoin(u, str(year)) for u in self.start_urls] | |
if month: | |
self.__start_urls = [ | |
urljoin(u, datetime.date(month=month).strftime('%M')) | |
for u in self.__start_urls] | |
def parse(self, response): | |
if response.status in (300, 301, 302, 404): | |
raise CloseSpider('No more urls to go') | |
entries = response.xpath( | |
"//div[@class='td-ss-main-content']//a[@rel='bookmark']") | |
titles = entries.xpath("text()").extract() | |
post_urls = entries.xpath("@href").extract() | |
for item in zip(titles, post_urls): | |
yield scrapy.Request(url=item[1], callback=self.parse_post, | |
dont_filter=True, | |
meta={'title': item[0]}, priority=1) | |
def parse_post(self, response): | |
date = response.xpath( | |
"//meta[@itemprop='datePublished']/@content").extract_first() | |
return {'title': response.meta['title'], 'datePublished': date} | |
def start_requests(self, number_of_pages=50): | |
# generate page IDs from 1000 down to 501 | |
for i in range(1, number_of_pages + 1): | |
if i > 1: | |
request_url = self.__start_urls[0] + '/page/%d' % i | |
else: | |
request_url = self.__start_urls[0] | |
yield scrapy.Request(url=request_url, callback=self.parse, | |
dont_filter=True, | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment