def search(self):
countTrial = 0
accepted = False
while not accepted and countTrial < self.__MAX_TRIALS:
countTrial += 1
response = urllib2.urlopen(self.VIDEO_SEARCH_BASE_URL +
self.__query)
html = response.read()
elements = re.findall(self.__REGEX_SEARCH_RESULT_ITEM, html)
if len(elements) >= self.__MIN_ACCEPTED_RESULTS:
accepted = True
for e in elements:
title = re.findall(self.__REGEX_TITLE_ATTR, e)[0].split('=')[1]
title = title[1:len(title) - 1]
title = title.strip().replace("\s+", ' ')
if String.count_match_words(self.__IGNORE_WORDS, title) > 0:
continue
vidId = re.findall(self.__REGEX_ID_ATTR, e)[0].split('=')[1]
vidId = vidId[1:len(vidId) - 1]
vidId = vidId.strip().replace("\s+", ' ')
self.__results.append({
self.__KEY_TITLE:
title,
self.__KEY_URL:
self.VIDEO_VIEW_BASE_URL + vidId
})
return len(self.__results)
def __get_next_video_url(self):
videoUrl = ""
keyWords = float(len(self.__keyword.split(' ')))
for i in range(self.__currentItemIdx + 1, len(self.__results)):
e = self.__results[i]
title = e[self.__KEY_TITLE]
points = String.count_match_words(self.__keyword, title) / keyWords
if points > self.__MIN_WORDS_ACCEPTED:
videoUrl = e[self.__KEY_URL]
self.__currentItemIdx = i
break
return videoUrl
def __get_next_video_url(self):
videoUrl = ""
keyWords = float(len(self.__keyword.split(' ')))
for i in range(self.__currentItemIdx+1, len(self.__results)):
e = self.__results[i]
title = e[self.__KEY_TITLE]
points = String.count_match_words(self.__keyword, title)/keyWords
if points > self.__MIN_WORDS_ACCEPTED:
videoUrl = e[self.__KEY_URL]
self.__currentItemIdx = i
break
return videoUrl
def __get_first_match_video_url(self):
maxPoints = .0
videoUrl = ""
keyWords = float(len(self.__keyword.split(' ')))
for i in range(0, len(self.__results)):
e = self.__results[i]
title = e[self.__KEY_TITLE]
points = String.count_match_words(self.__keyword, title) / keyWords
if points > maxPoints:
maxPoints = points
videoUrl = e[self.__KEY_URL]
self.__currentItemIdx = i
elif maxPoints > 0.:
break
return videoUrl
def __get_first_match_video_url(self):
maxPoints = .0
videoUrl = ""
keyWords = float(len(self.__keyword.split(' ')))
for i in range(0, len(self.__results)):
e = self.__results[i]
title = e[self.__KEY_TITLE]
points = String.count_match_words(self.__keyword, title)/keyWords
if points > maxPoints:
maxPoints = points
videoUrl = e[self.__KEY_URL]
self.__currentItemIdx = i
elif maxPoints > 0.:
break
return videoUrl
def search(self):
countTrial = 0
accepted = False
while not accepted and countTrial<self.__MAX_TRIALS:
countTrial += 1
response = urllib2.urlopen(self.VIDEO_SEARCH_BASE_URL + self.__query)
html = response.read()
elements = re.findall(self.__REGEX_SEARCH_RESULT_ITEM, html)
if len(elements) >= self.__MIN_ACCEPTED_RESULTS:
accepted = True
for e in elements:
title = re.findall(self.__REGEX_TITLE_ATTR, e)[0].split('=')[1]
title = title[1:len(title)-1]
title = title.strip().replace("\s+", ' ');
if String.count_match_words(self.__IGNORE_WORDS, title) > 0:
continue
vidId = re.findall(self.__REGEX_ID_ATTR, e)[0].split('=')[1]
vidId = vidId[1:len(vidId)-1]
vidId = vidId.strip().replace("\s+", ' ');
self.__results.append({
self.__KEY_TITLE: title, self.__KEY_URL: self.VIDEO_VIEW_BASE_URL+vidId
})
return len(self.__results)
