def downloadTrailer(trailerUrl, filePath):
""" Download the specified trailer.
@param trailerUrl: Trailer URL (ex: /trailer/the-terminal/trailer)
@param filePath: Path to save trailer
"""
trailerHtml = util.getHtml(trailerUrl)
videoNumbers = re.findall(VIDEONUM_REGEX, trailerHtml)
flashUrl = FLASH_URL.replace('{{videonum}}', videoNumbers[0])
flashResponse = util.getHtml(flashUrl)
fileUrl = re.findall(FLASH_REGEX, flashResponse)[0]
util.downloadFile(fileUrl, filePath)
def main():
htmls = util.getHtml(sys.argv, selenium, BOOKIE_NAME)
print("*************MAIN print htmls**********")
# print (htmls[0])
players = []
try:
fd = open("marathonbet_basket.csv", "w")
except:
print("Error while file creation")
print("----------------------------------------")
header = "ID,Local, Visitor, Date, 1., 2.\n"
fd.write(header)
counter = 1
for html in htmls:
print("+++++++++++++++++++++++++++++++++++++++")
print(html)
line = ""
players.extend(getTeams(html))
players.extend(getDate(html))
players.extend(getBets(html))
printable = set(string.printable)
line = str(counter) + ',' + str(getTeams(html)[0]) + ',' + str(
getTeams(html)[1]) + ',' + str(getDate(html)[0].replace(
'\n', '')) + ',' + str(getBets(html)[0]) + ',' + str(
getBets(html)[1]) + '\n'
fd.write(line)
counter = counter + 1
print("+++++++++++++++++++++++++++++++++++++++")
#util.output(sys.argv, players)
fd.close()
print(players)
def getTrailerUrls(movieUrl):
""" Return the trailers on the specified link.
@param movieUrl: URL to movie info on TrailerAddict
"""
tag = movieUrl.split('/')[-1]
movieHtml = util.getHtml(movieUrl)
movieRegex = MOVIE_REGEX.replace('{{tag}}', tag)
results = re.findall(movieRegex, movieHtml)
trailerUrls = map(lambda r: TABASE_URL.replace('{{path}}', r), results)
return list(set(trailerUrls)) # Remove Duplicates
def downloadTrailer(trailerUrl, filePath):
""" Download the specified trailer.
@param trailerUrl: Trailer URL (ex: /trailer/the-terminal/trailer)
@param filePath: Path to save trailer
"""
videoHtml = util.getHtml(trailerUrl)
videoId = re.findall(ID_REGEX, trailerUrl)[0][0]
tParam = re.findall(T_PARAM_REGEX, videoHtml)[0]
fileUrl = VIDEO_URL % (videoId, tParam)
util.downloadFile(fileUrl, filePath)
def crawlGooseUserList():
#this function useless, need to login first
req = loginWeibo()
#req = requests
base_url = 'http://d.weibo.com/230771_-_EXPERTUSER?page=%d#Pl_Core_F4RightUserList__4'
page_num = 22
for page_index in range(1, page_num):
url = base_url % page_index
path = 'tmp'
r = getHtml(url, path, req = req, save = 'db')
print r
break
def search(title):
""" Search for the specified movie.
@param title: Title of the movie to search for
"""
# Fetch the HTML for the search page
query = title.replace(" ", "+")
searchUrl = SEARCH_URL.replace('{{query}}', query)
searchHtml = util.getHtml(searchUrl)
results = re.findall(SEARCH_REGEX, searchHtml)
# Parse and return the search results
searchResults = []
for result in results:
searchResult = {}
searchResult['url'] = TABASE_URL.replace('{{path}}', result[0])
searchResult['title'] = result[1]
searchResult['year'] = result[2]
searchResults.append(searchResult)
return searchResults
def getUserWeibo(req=requests):
user = getUserList()
for u in user:
print u,'begin'
u = u.strip()
base_url = 'http://weibo.cn/%s?filter=1&page=' % u
print base_url
pagenum = 200
getnum = False
i = 1
while i <= pagenum:
url = base_url + str(i)
print url
try:
r = getHtml(url, '', req = req, save = 'db', tag='second')
if getnum == False:
pagenum = getPageNum(r)
getnum = True
except:
pass
i += 1
print u,'done'
return r
def main():
htmls = util.getHtml(sys.argv, selenium, BOOKIE_NAME)
players = []
for html in htmls:
players.extend(getPlayers(html))
util.output(sys.argv, players)
def main():
htmls = util.getHtml(sys.argv, selenium, BOOKIE_NAME)
players = []
for html in htmls:
players.extend(getPlayers(html))
util.printPlayers(players)