def fetchaipai(gameName, startfrom, endto, gameidx, save=True):
videoCount = 0
addCount = 0
# open bad link
urls = []
with open("%s/pyspider/aipaibadlink2.list" % projectPathBase, "r") as badList:
for l in badList:
urls.append(l.strip())
gameidx = 0
for idx in range(startfrom, endto):
url = "%s%s%s%d.html" % ( URLBase, urllib.quote(gameName), URLPage, idx)
print url
if len(url) < 5:
gameidx = int(url)
with open("%s/pyspider/aipaibadlink3.list" % projectPathBase, "a") as badfile:
badfile.write("%d\n" % gameidx)
continue
opener = urllib2.OpenerDirector()
handler = urllib2.HTTPHandler()
opener.add_handler(handler)
opener.addheaders = [('User-agent', 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)')]
content_stream = opener.open(url)
content = content_stream.read()
store.savePage("indexaipai.html", content)
soupContent = bs4.BeautifulSoup(content)
mainContents = soupContent.select(".mod_svlist")
if len(mainContents) <= 0:
with open("%s/pyspider/aipaibadlink3.list" % projectPathBase, "a") as badfile:
badfile.write("%s\n" % url)
continue
mainContentList = soupContent.select(".mod_svlist")[0]
vs = mainContentList.select("li")
if len(vs) <= 0:
break
hrefList = []
titleList = []
log_vidList = []
playtimeList = []
pubdateList = []
uploaderList = []
playCountList = []
tagsList = []
for v in vs:
linkA = v.select(".com_v_tit")[0]
# title, href
title = linkA['title']
href = linkA['href']
print title, href
lastslash = href.rfind("/")
lastdot = href.rfind(".")
# log_vid
log_vid = href[lastslash+1:lastdot]
print log_vid,
# img
linkImg = v.select(".pic")[0]
thumbImg = linkImg.select("img")[0]
thumbImgSrc = thumbImg['src']
# with open("aipaiImg.list", "a") as imgListFile:
# imgListFile.write("%s.jpg:%s\n" % (log_vid, thumbImgSrc))
# urllib.urlretrieve(thumbImgSrc, "%s/%s.jpg" % (storePath, log_vid))
# tags
tagsA = v.select(".tag")[0]
tagsAs = tagsA.select("a")
tags = []
for tagA in tagsAs:
tags.append(tagA.get_text())
tagStr = ";".join(tags)
infoDiv = v.select(".info")[0]
infos = infoDiv.select("em")
# playCount
playCount = int(infos[0].get_text())
print playCount,
datestr = infos[2].get_text()
print datestr,
pubdate = None
noletter = re.sub("[^0-9]", "", datestr)
if datestr.find(u"周") >= 0 or datestr.find(u"星期") >= 0:
pubdate = datetime.today()-relativedelta(weeks=int(noletter))
elif datestr.find(u"天") >= 0:
pubdate = datetime.today()-relativedelta(days=int(noletter))
elif datestr.find(u"小时") >= 0:
pubdate = datetime.today()-relativedelta(hours=int(noletter))
elif datestr.find(u"分钟") >= 0:
pubdate = datetime.today()-relativedelta(minutes=int(noletter))
elif datestr.find(u"秒") >= 0:
pubdate = datetime.today()-relativedelta(seconds=int(noletter))
else:
pubdate = datetime.strptime(datestr, "%Y-%m-%d").date()
# pubdate
print pubdate
authorA = infoDiv.select(".hr_zz")[0]
# uploader
uploader = authorA.get_text()
print uploader
hrefList.append(href)
titleList.append(title)
log_vidList.append(log_vid)
pubdateList.append(pubdate)
uploaderList.append(uploader)
playCountList.append(playCount)
tagsList.append(tagStr)
videoCount = videoCount + 1
count = len(playCountList)
if save == True:
for i in range(count):
addCount = addCount + store.storeVideo(titleList[i], hrefList[i], log_vidList[i], uploaderList[i], playCountList[i], pubdateList[i], "4", gameidx, tagsList[i], thumbImgSrc)
print log_vidList[i], uploaderList[i], playCountList[i], pubdateList[i], thumbImgSrc
time.sleep(5)
return videoCount, addCount
def fetchYouku(gameName, startfrom, endto, gameidx, save=True):
videoCount = 0
addCount = 0
for idx in range(startfrom, endto):
url = "%s%s%s%d%s" % ( sokuURLBase, urllib.quote(gameName),sokuURLPage, idx, sokuURLOther)
print url
opener = urllib2.OpenerDirector()
handler = urllib2.HTTPHandler()
opener.add_handler(handler)
opener.addheaders = [('User-agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11')]
content_stream = opener.open(url)
content = content_stream.read()
# store.savePage("index.html", content)
soupContent = bs4.BeautifulSoup(content)
mainResults = soupContent.select(".sk_result")
if len(mainResults) <= 0:
break
mainResult = mainResults[0]
vs = mainResult.select(".v")
if len(vs) <= 0:
break
for v in vs:
meta = v.select(".v-meta")[0]
metaTitle = meta.select(".v-meta-title")[0]
linkA = metaTitle.select("a")[0]
title = linkA['title']
href = linkA['href']
log_vid = linkA['_log_vid']
metaEntry = meta.select(".v-meta-entry")[0]
metaDatas = metaEntry.select(".v-meta-data")
thumbDiv = v.select(".v-thumb")[0]
thumbImg = thumbDiv.select("img")[0]
thumbImgSrc = thumbImg["src"]
# urllib.urlretrieve(thumbImgSrc, "%s/%s.jpg" % (storePath, log_vid))
# with open("youkuPic.list", "a") as picFile:
# picFile.write("%s.jpg:%s\n" % (log_vid, thumbImgSrc))
uploader = ""
playtime = 0
publishdate = datetime.today()
for mdata in metaDatas:
mlabel = mdata.select("label")[0]
labelText = mlabel.get_text().strip()
mspan = mdata.select("span")[0]
spanText = mspan.get_text().strip()
if labelText.startswith(u"用户"):
uploader = spanText
elif labelText.startswith(u"播客"):
uploader = spanText
elif labelText.startswith(u"播放"):
noletter = re.sub("[^0-9]", "", spanText)
playtime = int(noletter)
elif labelText.startswith(u"发布"):
noletter = re.sub("[^0-9]", "", spanText)
if spanText.find(u"秒") >= 0:
publishdate = publishdate-relativedelta(seconds=int(noletter))
elif spanText.find(u"分钟") >= 0:
publishdate = publishdate-relativedelta(minutes=int(noletter))
elif spanText.find(u"小时") >= 0:
publishdate = publishdate-relativedelta(hours=int(noletter))
elif spanText.find(u"天") >= 0:
publishdate = publishdate-relativedelta(days=int(noletter))
elif spanText.find(u"周") >= 0:
publishdate = publishdate-relativedelta(weeks=int(noletter))
elif spanText.find(u"月") >= 0:
publishdate = publishdate-relativedelta(months=int(noletter))
elif spanText.find(u"年") >= 0:
publishdate = publishdate-relativedelta(years=int(noletter))
print uploader, playtime, publishdate, thumbImgSrc
if save == True:
addCount = addCount + store.storeVideo(title, href, log_vid, uploader, playtime, publishdate, "1", gameidx, "", thumbImgSrc)
videoCount = videoCount + 1
time.sleep(5)
return videoCount, addCount
