Last active
July 6, 2016 05:35
-
-
Save whatvn/9be2d2894a95db93ed0853647dca24c2 to your computer and use it in GitHub Desktop.
download all radio espisode from theoyeucau.com in one shot
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 re | |
from collections import OrderedDict | |
import os | |
import urllib2 | |
ESPISODE_LINK="http://www.theoyeucau.com/episode" | |
ESPISODE_LINK_REGEX = re.compile("http\:\/\/www\.theoyeucau\.com\/episode\/[a-zA-Z-]+\/") | |
# http://www.theoyeucau.com/wp-content/uploads/sites/3/2015/12/Tai-sao-phai-song-nhu-mot-con-nguoi.mp3 | |
VIETNAMESE="".join([ch.encode('utf8') for ch in unicode("ạảãàáâậầấẩẫăắằặẳẵóòọõỏôộổỗồốơờớợởỡéèẻẹẽêếềệểễúùụủũưựữửừứíìịỉĩýỳỷỵỹđ", 'utf8')]) | |
ESPISODE_MP3_LINK_REGEX=re.compile("http\:\/\/www\.theoyeucau.com\/wp-content\/uploads\/sites\/\d+\/\d+\/\d+\/[a-zA-Z -._\d" + VIETNAMESE + "]+\.mp3") | |
FALLBACK_MP3_REGEX=re.compile("http\:\/\/www\.theoyeucau.com\/wp-content\/uploads\/sites\/\d+\/Shows\/[a-zA-Z -._\d]+\/[a-zA-Z -_.\d]+\/[a-zA-Z -._\d" + VIETNAMESE + "]+\.mp3") | |
# http://www.theoyeucau.com/wp-content/uploads/sites/3/Shows/Ket noi yeu thuong/2012/2012-07-05 Ta muon hoc cach quen nguoi/Ket noi yeu thuong - Ta muon hoc cach quen nguoi - episode_81622 - track_0_81623 - Ta muon hoc cach quen nguoi.mp | |
PROCESSED_LINKS = [ l.strip() for l in open("links.txt").readlines() ] if os.path.exists("links.txt") else [] | |
def getLinkContent(link): | |
req = urllib2.Request(link) | |
req.add_header("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36") | |
req.add_header("Accept", "*/*") | |
req.add_header("Connection", "keep-alive") | |
req.add_header("Accept-Encoding", "identity;q=1, *;q=0, val") | |
response = urllib2.urlopen(req) | |
return response.read() | |
def getPageLink(pageNum): | |
return ESPISODE_LINK + "/page/" + str(pageNum) + "/" | |
def getEspisodeLink(pageNum): | |
print "Processing page num: " + str(pageNum) | |
pageLink = getPageLink(pageNum) | |
pageContent = getLinkContent(pageLink) | |
result = filter(lambda l: "page" not in l and "feed" not in l, list(OrderedDict.fromkeys(ESPISODE_LINK_REGEX.findall(pageContent)))) | |
return result | |
def getMp3Link(espisodeLink): | |
print "Get mp3 link on page " + espisodeLink | |
pageContent = getLinkContent(espisodeLink) | |
try: | |
result = ESPISODE_MP3_LINK_REGEX.findall(pageContent)[0] if len(ESPISODE_MP3_LINK_REGEX.findall(pageContent)) > 0 else FALLBACK_MP3_REGEX.findall(pageContent)[0] | |
return result | |
except IndexError: # page without mp3 file available | |
print "They lost its content" | |
return None | |
def downloadMp3(mp3Link, espisodeLink): | |
if mp3Link == None: return | |
print "Download " + mp3Link | |
year = mp3Link.split("/")[7] | |
try: | |
os.mkdir(year) | |
except OSError: | |
pass | |
try: | |
with open(year + "/" + mp3Link.split("/")[-1],'wb') as mp3: mp3.write(getLinkContent(mp3Link)) | |
except urllib2.HTTPError: | |
import urllib | |
urllib.urlretrieve(mp3Link, year + "/" + mp3Link.split("/")[-1]) | |
# not to download link already downloaded | |
with open("links.txt", 'a+') as f: f.write(espisodeLink + "\n") | |
def downThemAll(pageNum): | |
linkList = filter(lambda l: l not in PROCESSED_LINKS, getEspisodeLink(pageNum)) | |
for l in linkList: downloadMp3(getMp3Link(l), l) | |
if __name__ == '__main__': | |
for i in range(1, 117): downThemAll(i) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment