python爬虫爬取Bloomberg新闻

# Bot rules:
# 1. A bot may not injure a human being or, through inaction, allow a human being to come to harm.
# 2. A bot must obey orders given it by human beings except where such orders would conflict with the First Law.
# 3. A bot must protect its own existence as long as such protection does not conflict with the First or Second Law.
# If you can read this then you should apply here https://www.bloomberg.com/careers/
User-agent: *
Disallow: /news/live-blog/2016-03-11/bank-of-japan-monetary-policy-decision-and-kuroda-s-briefing
Disallow: /polska
User-agent: Mediapartners-Google*
Disallow: /about/careers
Disallow: /about/careers/
Disallow: /offlinemessage/
Disallow: /apps/fbk
Disallow: /bb/newsarchive/
Disallow: /apps/news
Sitemap: https://www.bloomberg.com/feeds/bbiz/sitemap_index.xml
Sitemap: https://www.bloomberg.com/feeds/bpol/sitemap_index.xml
Sitemap: https://www.bloomberg.com/feeds/bview/sitemap_index.xml
Sitemap: https://www.bloomberg.com/feeds/gadfly/sitemap_index.xml
Sitemap: https://www.bloomberg.com/feeds/quicktake/sitemap_index.xml
Sitemap: https://www.bloomberg.com/bcom/sitemaps/people-index.xml
Sitemap: https://www.bloomberg.com/bcom/sitemaps/private-companies-index.xml
Sitemap: https://www.bloomberg.com/feeds/bbiz/sitemap_securities_index.xml
User-agent: Spinn3r
Disallow: /podcasts/
Disallow: /feed/podcast/
Disallow: /bb/avfile/
User-agent: Googlebot-News
Disallow: /sponsor/
Disallow: /news/sponsors/*

<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
<sitemap>
<loc>
https://www.bloomberg.com/feeds/gadfly/sitemap_recent.xml
</loc>
<lastmod>2017-02-17T07:46:07-05:00</lastmod>
</sitemap>
<sitemap>
<loc>
https://www.bloomberg.com/feeds/gadfly/sitemap_news.xml
</loc>
<lastmod>2017-02-17T07:46:07-05:00</lastmod>
</sitemap>
<sitemap>
<loc>
https://www.bloomberg.com/feeds/gadfly/sitemap_2017_2.xml
</loc>
<lastmod>2017-02-17T07:46:07-05:00</lastmod>
</sitemap>

<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:news="http://www.google.com/schemas/sitemap-news/0.9" xmlns:image="http://www.google.com/schemas/sitemap-image/1.1">
<url>
<loc>
https://www.bloomberg.com/gadfly/articles/2017-02-17/luxury-tax
</loc>
<news:news>
<news:publication>
<news:name>Bloomberg</news:name>
<news:language>en</news:language>
</news:publication>
<news:title>Giving U.S. Border Tax a European Luxury Snub</news:title>
<news:publication_date>2017-02-17T10:43:15.284Z</news:publication_date>
<news:keywords>
Sales Tax, Jobs, China, Europe, Ralph Lauren, Michael David Kors, Bernard Arnault, Donald John Trump, Miuccia Prada Bianchi
</news:keywords>
<news:stock_tickers>LON:BRBY, EPA:MC, LON:BARC, EPA:KER</news:stock_tickers>
</news:news>
<image:image>
<image:loc>
https://assets.bwbx.io/images/users/iqjWHBFdfxIU/iurmUVIRXTqY/v0/1200x-1.jpg
</image:loc>
<image:license>https://www.bloomberg.com/tos</image:license>
</image:image>
</url>

# -*- coding: utf-8 -*-
#可以下载网站的sitemap
import re
from downloader import Downloader #downloader的作用是下载网页内容
D = Downloader()file1 = open('sitemaps.txt','a')
file2 = open('htmls.txt','a')
def crawl_sitemap(url):#download sitemap filesitemap = D(url)#extract the sitemap linkslinks = re.findall('<loc>(.*?)</loc>',sitemap)#download each linkfor link in links:file1.write(link)file1.write('\n')html = D(link)file2.write(html)file2.write('\n')
crawl_sitemap('https://www.bloomberg.com/feeds/gadfly/sitemap_index.xml')#上面四个红色的sitemap，这里就放了一个，没有写到一起。file1.close()
file2.close()

import urlparse
import urllib2
import random
import time
from datetime import datetime, timedelta
import socketDEFAULT_AGENT = 'wswp'
DEFAULT_DELAY = 5
DEFAULT_RETRIES = 1
DEFAULT_TIMEOUT = 60class Downloader:def __init__(self, delay=DEFAULT_DELAY, user_agent=DEFAULT_AGENT, proxies=None, num_retries=DEFAULT_RETRIES,timeout=DEFAULT_TIMEOUT, opener=None, cache=None):socket.setdefaulttimeout(timeout)self.throttle = Throttle(delay)self.user_agent = user_agentself.proxies = proxiesself.num_retries = num_retriesself.opener = openerself.cache = cachedef __call__(self, url):result = Noneif self.cache:try:result = self.cache[url]except KeyError:# url is not available in cachepasselse:if self.num_retries > 0 and 500 <= result['code'] < 600:# server error so ignore result from cache and re-downloadresult = Noneif result is None:# result was not loaded from cache so still need to downloadself.throttle.wait(url)proxy = random.choice(self.proxies) if self.proxies else Noneheaders = {'User-agent': self.user_agent}result = self.download(url, headers, proxy=proxy, num_retries=self.num_retries)if self.cache:# save result to cacheself.cache[url] = resultreturn result['html']def download(self, url, headers, proxy, num_retries, data=None):print 'Downloading:', urlrequest = urllib2.Request(url, data, headers or {})opener = self.opener or urllib2.build_opener()if proxy:proxy_params = {urlparse.urlparse(url).scheme: proxy}opener.add_handler(urllib2.ProxyHandler(proxy_params))try:response = opener.open(request)html = response.read()code = response.codeexcept Exception as e:print 'Download error:', str(e)html = ''if hasattr(e, 'code'):code = e.codeif num_retries > 0 and 500 <= code < 600:# retry 5XX HTTP errorsreturn self._get(url, headers, proxy, num_retries - 1, data)else:code = Nonereturn {'html': html, 'code': code}def _get(self, url, headers, proxy, param, data):passclass Throttle:"""Throttle downloading by sleeping between requests to same domain"""def __init__(self, delay):# amount of delay between downloads for each domainself.delay = delay# timestamp of when a domain was last accessedself.domains = {}def wait(self, url):"""Delay if have accessed this domain recently"""domain = urlparse.urlsplit(url).netloclast_accessed = self.domains.get(domain)if self.delay > 0 and last_accessed is not None:sleep_secs = self.delay - (datetime.now() - last_accessed).secondsif sleep_secs > 0:time.sleep(sleep_secs)self.domains[domain] = datetime.now()

import re
file = open('./sitemap_and_html_waiting_to_be_crawled/htmls_gadfly.txt')
file2 = open('htmls.txt','a')for temp in file.readlines():if re.match('<loc>',temp.strip()) is None:passelse:print temp#file2.write(temp)#file2.write('\n')
file.close()
file2.close()

scrapy startproject linkcrawler

import scrapy
file = open('G:\onedrive\workspace\crawler\htmls\htmls_gadfly.txt')#这里是之前html文件的地址
data = file.readlines()def list_to_string(list):string = ""for i in list:string += i.strip()return stringclass LinkCrawler(scrapy.Spider):name = "link"def start_requests(self):"""urls = ['https://www.bloomberg.com/gadfly/articles/2017-02-16/baidu-failing-fast-is-a-smart-move-to-build-a-future','https://www.bloomberg.com/gadfly/articles/2017-02-13/gaslog-partners-poised-for-lng-market-recovery','https://www.bloomberg.com/gadfly/articles/2017-02-07/bp-earnings-today-doesn-t-match-tomorrow']:return:"""for url in data:yield scrapy.Request(url=url, callback=self.parse)def parse(self, response): #这里是比较关键的部分，主要用了css选择器，选择需要的部分，下面会详细讲yield{'title': response.css('h1.headline_4rK3h>a::text').extract_first(),'time_1': response.css("time::text").extract_first().strip(),'time_2': response.css('time').re(r'datetime="\s*(.*)">')[0],'content': list_to_string(response.css('div.container_1KxJx>p::text').extract())}file.close()

scrapy crawl link -o news.json

 经过一段时间的运行，就把所有的新闻保存在一个news.json文件中了。

response.css('h1.headline_4rK3h>a::text').extract_first()

总结