def scribe(video_id: str, youtube_api_key: str):
if not youtube_api_key:
log.error(
'You need to provide an API key either by --youtube-api0key or by setting YOUTUBE_API_KEY'
)
sys.exit(1)
api = Api(api_key=youtube_api_key)
video_metadata = api.get_video_by_id(video_id=video_id).items[0]
#log.debug(json.dumps(video_metadata.to_dict(), sort_keys=True, indent=2))
title = video_metadata.snippet.title
preview_image_path = get_preview_image(
img_url=video_metadata.snippet.thumbnails.default.url,
video_id=video_id)
description = video_metadata.snippet.description
date = datetime.datetime.strptime(video_metadata.snippet.publishedAt,
"%Y-%m-%dT%H:%M:%S%z")
captions = YouTubeTranscriptApi.get_transcript(video_id)
print(
gen_markdown_page(video_id=video_id,
title=title,
image_path=preview_image_path,
description=description,
date=date,
captions=captions))
class YTSearch():
def __init__(self, api_key=API_KEY):
self.key = api_key
self.api = Api(api_key=self.key)
def check_video_eligibility(self, ids, expected_type):
like_max = {"yt_id": "", "youtube_rating": 0.0}
for id in ids:
video = list(
self.api.get_video_by_id(video_id=id).to_dict().items())
try:
vid = video[5][1][0]
duration = isodate.parse_duration(
vid['contentDetails']['duration']).total_seconds()
definition = vid['contentDetails']['definition']
like_count = float(vid["statistics"]["likeCount"])
dislike_count = float(vid["statistics"]["dislikeCount"])
duration_min = Duration[expected_type][0]
duration_max = Duration[expected_type][1]
like_percentage = like_count / (like_count + dislike_count)
channel_title = vid["snippet"]["channelTitle"]
if like_percentage > like_max["youtube_rating"] and (duration_min < duration <= duration_max) and \
channel_title != 'YouTube Movies':
like_max["yt_id"] = id
like_max["yt_duration"] = duration
like_max["yt_likes"] = like_count
like_max["youtube_rating"] = like_percentage
like_max["yt_definition"] = definition
except Exception as e:
print("ignoring the error")
continue
return like_max
def obsolete_get_stats(self,
key_word,
expected_type="movie",
max_results=10):
videos = list(
self.api.search_by_keywords(q=key_word,
search_type=["video"]).items)
vids = [vid.to_dict()["id"]['videoId'] for vid in videos]
ret = self.check_video_eligibility(vids, expected_type)
print(ret)
def get_youtube_stats(self,
key_word,
expected_type="movie",
max_results=10):
get_mov_stats = YoutubeSearch(key_word,
max_results=max_results).to_dict()
ids = [d['id'] for d in get_mov_stats]
ret = self.check_video_eligibility(ids, expected_type)
for mov in get_mov_stats:
if mov["id"] == ret["yt_id"]:
ret["youtube_link"] = "https://youtube.com" + mov["link"]
return (ret)
def process_play_list_step(message):
try:
chat_id = message.chat.id
text = message.text
if ":" not in text:
bot.reply_to(message, 'Wrong message format')
return
data = str(text).split(':')
plaid = data[0]
title = data[1]
if len(plaid) <= 5 or len(title) <= 5:
bot.reply_to(message, 'Wrong message format')
return
api = Api(api_key=youtube_api_key)
playlist_item_by_playlist = api.get_playlist_items(playlist_id=plaid,
count=1000)
videos = playlist_item_by_playlist.items
if len(videos) <= 0:
bot.send_message(message.chat.id,
"No Vidoes found for playlist = " + str(title))
return
bot.send_message(message.chat.id,
"Found " + str(len(videos)) + " videos from youtube")
real_video_count = len(videos)
count = 0
lessons = []
for video in videos:
video_by_id = api.get_video_by_id(
video_id=video.snippet.resourceId.videoId,
parts=('snippet', 'contentDetails', 'statistics'))
if len(video_by_id.items) <= 0:
real_video_count = real_video_count - 1
continue
count = count + 1
item = video_by_id.items[0]
title = title + " " + formatLessonName(
count) + " " + item.snippet.title
time_val = isodate.parse_duration(item.contentDetails.duration)
code = getYoutubeEmbedCode(video.snippet.resourceId.videoId)
lesson = Lesson(title, code, time_val)
lessons.append(lesson)
bot.send_message(
message.chat.id,
"Total avalibale vidoe count = " + str(real_video_count))
if len(lessons) <= 0:
bot.send_message(message.chat.id, "No lesson found!")
loginAndUpdate(lessons, message, plaid)
except Exception as e:
bot.reply_to(message, str(e))
def get_youtube_statistics(video_ids):
api_key = frappe.db.get_single_value("Video Settings", "api_key")
api = Api(api_key=api_key)
try:
video = api.get_video_by_id(video_id=video_ids)
video_stats = video.items
return video_stats
except Exception:
title = "Failed to Update YouTube Statistics"
frappe.log_error(title + "\n\n" + frappe.get_traceback(),
title=title)
def set_youtube_statistics(self):
api_key = frappe.db.get_single_value("Video Settings", "api_key")
api = Api(api_key=api_key)
try:
video = api.get_video_by_id(video_id=self.youtube_video_id)
video_stats = video.items[0].to_dict().get('statistics')
self.like_count = video_stats.get('likeCount')
self.view_count = video_stats.get('viewCount')
self.dislike_count = video_stats.get('dislikeCount')
self.comment_count = video_stats.get('commentCount')
except Exception:
title = "Failed to Update YouTube Statistics for Video: {0}".format(
self.name)
frappe.log_error(title + "\n\n" + frappe.get_traceback(),
title=title)
# Then create another nested folder. Example: output/output-2020-09-14T173551
outputFolderPath = join(
'output', 'output-' + strftime('%Y-%m-%dT%H%M%S', localtime()))
mkdir(outputFolderPath)
# Remember to comment out the individual playlist keys from MyConfigurations if you don't want to loop through them all
for key in playlistIDs:
playlistVideoItems = api.get_playlist_items(
playlist_id=playlistIDs[key], count=None).items
currentTimestamp = strftime(' %Y-%m-%dT%H%M%S', localtime())
outputFileName = key + currentTimestamp + '.out'
outputFilePath = join(outputFolderPath, outputFileName)
with open(outputFilePath, 'w', encoding='utf8') as outfile:
for index, playlistVideo in enumerate(playlistVideoItems):
try:
video = api.get_video_by_id(
video_id=playlistVideo.contentDetails.videoId).items[0]
if not isVideoBlocked(countryCode, video):
outfile.write(video.snippet.title + '\n')
if displayUploader:
outfile.write(f'{video.snippet.channelTitle}\n\n')
except Exception as e:
print(
f'\n\nException occurred on "{playlistVideo.snippet.title}" within playlist {key} at index {index}: {e}'
)
class EdumaBot():
def __init__(self):
self.driver = webdriver.Chrome()
self.api = Api(api_key=apikey)
self.db = DBHelper()
def login(self):
self.driver.get(url)
time.sleep(1)
login_btn = self.driver.find_element_by_xpath('//*[@id="wp-submit"]')
email_field = self.driver.find_element_by_xpath(
'//*[@id="user_login"]')
pass_field = self.driver.find_element_by_xpath('//*[@id="user_pass"]')
email_field.send_keys(username)
time.sleep(1)
pass_field.send_keys(password)
login_btn.click()
self.driver.find_element_by_xpath(
'//*[@id="toplevel_page_learn_press"]').click()
self.driver.find_element_by_xpath(
'//*[@id="toplevel_page_learn_press"]/ul/li[3]/a').click()
self.driver.find_element_by_xpath(
'//*[@id="wpbody-content"]/div[3]/a').click()
def start(self):
self.login()
courses = []
# resume_lesons = self.db.get_resume_lessons()
#
# print(resume_lesons.rowcount)
#
# if resume_lesons.rowcount != -1:
# for ressume_lesson in resume_lesons:
# index = ressume_lesson[4]
# total = ressume_lesson[3]
# title = ressume_lesson[2]
# playlist_id = ressume_lesson[1]
#
# if int(index) == int(total):
# continue
#
# print("found lesons that is not added index = {} ,playlist = {},count = {} ".format(index, playlist_id,
# total))
# courses.append(Course(title=str(title), playlistId=str(playlist_id), start=str(index + 1)))
f = open("playlist", "r+")
for i in f:
k = i.split('\n')
for j in k:
vals = j.split("[|]")
if len(vals) == 2:
courses.append(
Course(title=str(vals[1]),
playlistId=str(vals[0]),
start=0))
if len(courses) == 0:
print("no lesson found on file = " + f.name)
return
print("course found on file " + str(len(courses)))
for course in courses:
finsihed = self.db.getFinishedPlayLists(
playlist_id=course.playlistId)
print(finsihed)
if finsihed.rowcount != -1:
print("course already exist titile = " + course.title)
continue
playlist_item_by_playlist = self.api.get_playlist_items(
playlist_id=course.playlistId, count=1000)
videos = playlist_item_by_playlist.items
print("number of vidoes in playlist = " + str(len(videos)))
if len(videos) <= 0:
print("no videos found for playlist = " +
str(course.playlistId) + "\n")
continue
count = 1
real_video_count = len(videos)
lesson_list = []
temp_counter = 0
for video in videos:
temp_counter = temp_counter + 1
if temp_counter <= -1 and course.playlistId == "":
continue
count = temp_counter
video_by_id = self.api.get_video_by_id(
video_id=video.snippet.resourceId.videoId,
parts=('snippet', 'contentDetails', 'statistics'))
if len(video_by_id.items) <= 0:
print("missed or private vidoe for = " +
str(course.playlistId) + "\n")
real_video_count = real_video_count - 1
continue
item = video_by_id.items[0]
title = course.title + " " + self.formatLessonName(
count) + " " + item.snippet.title
time_val = isodate.parse_duration(item.contentDetails.duration)
code = self.getYoutubeEmbedCode(
video.snippet.resourceId.videoId)
count = count + 1
lesson = Lesson(title, code, time)
title_field = self.driver.find_element_by_xpath(
'//*[@id="title"]')
media_field = self.driver.find_element_by_xpath(
'//*[@id="_lp_lesson_video_intro"]')
date_field = self.driver.find_element_by_xpath(
'//*[@id="_lp_duration"]')
publish_button = self.driver.find_element_by_xpath(
'//*[@id="publish"]')
select = Select(
self.driver.find_element_by_id('_lp_duration_select'))
time_array = str(time_val).split(":")
print(time_array[0] + " = hour")
print(time_array[1] + " = minties")
final_time = 1
if time_array[0] != "0" and time_array[0] != "00":
select.select_by_value('hour')
final_time = time_array[0]
elif time_array[1] != "0" and time_array[1] != "00":
select.select_by_value('minute')
final_time = time_array[1]
else:
select.select_by_value('minute')
title_field.clear()
title_field.send_keys(lesson.title)
time.sleep(1)
media_field.clear()
media_field.send_keys(lesson.code)
time.sleep(1)
date_field.clear()
date_field.send_keys(final_time)
time.sleep(2)
self.driver.execute_script("arguments[0].click();",
publish_button)
self.driver.implicitly_wait(10)
time.sleep(2)
self.driver.find_element_by_xpath(
'//*[@id="wpbody-content"]/div[3]/a').click()
self.driver.implicitly_wait(10)
#self.db.update_lessons_resume(playlist_id=course.playlistId, index=str(temp_counter))
# suffucly addded the playlsit
# self.db.add_finished_playlist(course.playlistId)
# self.db.delete_course_from_resume(playlist_id=course.playlistId)
def formatLessonName(self, count):
countStr = ""
if count <= 9:
countStr = "00" + str(count)
elif count <= 99 and count >= 10:
countStr = "0" + str(count)
else:
countStr = str(count)
return countStr
def getYoutubeEmbedCode(self, videoId):
embedder = Embedder()
code = embedder("https://www.youtube.com/watch?v=" + str(videoId),
width=video_width,
height=video_height)
return code
