[Crawler] Get Title from web-ptt

[Crawler] Get Title from web-ptt

	# Python3.5
	# OS: Windows7
	# IDE: PyCharm
	# 擷取Ptt電影版文章之日期、作者、標題
	# http://jialin128.pixnet.net/blog/post/106647560-%5Bpython%5D-ptt-crawler-in-python-%E4%BD%BF%E7%94%A8python%E7%88%AC%E6%89%B9%E8%B8%A2%E8%B8%A2
	import urllib.request
	# http://stackoverflow.com/questions/33331850/importerror-no-module-named-bs4-in-windows
	from bs4 import BeautifulSoup
	# http://stackoverflow.com/questions/16627227/http-error-403-in-python-3-web-scraping
	from urllib.request import Request, urlopen
	req = Request('https://www.ptt.cc/bbs/movie/index.html', headers={'User-Agent': 'Mozilla/5.0'})
	response = urlopen(req).read()
	soup = BeautifulSoup(response,"html.parser")
	container = soup.select('.r-ent')
	for each_item in container:
	print ("日期："+each_item.select('div.date')[0].text, "作者："+each_item.select('div.author')[0].text)
	print (each_item.select('div.title')[0].text)
	print ("---------------------------------")

view raw python_web_ptt_title hosted with ❤ by GitHub