def get_popular_links(input_time=config_pytomo.TIME_FRAME,
max_results=config_pytomo.MAX_PER_PAGE):
'''Returns the most popular dailymotion links for France.
The country should be set as parameter in start_pytomo if user should
specify it.
The number of videos returned is given as Total_pages.
(The results returned are in no particular order).
A set of only dailymotion links from url
'''
config_pytomo.LOG.debug('Getting popular links per country')
time_frame = get_time_frame(input_time)
if max_results > MAX_VIDEO_PER_PAGE:
pages = int(max_results) / MAX_VIDEO_PER_PAGE
else:
pages = 1
for page in xrange(pages):
url = CHARTS_URL.format(country=COUNTRY,
time_frame=time_frame,
page=(page + 1))
links = lib_links_extractor.get_all_links(url)
if not links:
config_pytomo.LOG.warning('No popular link was found')
popular_links = set()
for link in links:
if link.find(r'/video/') >= 0:
if link.startswith('/'):
link = ''.join((DM_LINK, link))
popular_links.add(link)
if len(popular_links) >= max_results:
break
return popular_links
def get_popular_links(input_time=config_pytomo.TIME_FRAME,
max_results=config_pytomo.MAX_PER_PAGE):
'''Returns the most popular dailymotion links for France.
The country should be set as parameter in start_pytomo if user should
specify it.
The number of videos returned is given as Total_pages.
(The results returned are in no particular order).
A set of only dailymotion links from url
'''
config_pytomo.LOG.debug('Getting popular links per country')
time_frame = get_time_frame(input_time)
if max_results > MAX_VIDEO_PER_PAGE:
pages = int(max_results) / MAX_VIDEO_PER_PAGE
else:
pages = 1
for page in xrange(pages):
url = CHARTS_URL.format(country=COUNTRY, time_frame=time_frame,
page=(page + 1))
links = lib_links_extractor.get_all_links(url)
if not links:
config_pytomo.LOG.warning('No popular link was found')
popular_links = set()
for link in links:
if link.find(r'/video/') >= 0:
if link.startswith('/'):
link = ''.join((DM_LINK, link))
popular_links.add(link)
if len(popular_links) >= max_results:
break
return popular_links
def get_youtube_links(url, max_per_page):
"Return a set of only Youtube links from url"
if not ('youtube' in url or 'youtu.be' in url):
config_pytomo.LOG.error("Only youtube is implemented, got url: %s"
% url)
return []
links = lib_links_extractor.get_all_links(url)
youtube_links = set()
config_pytomo.LOG.info("Found %d links for url %s" % (len(links), url))
for link in links:
if link.find("/watch") >= 0:
if link.startswith('/'):
link = ''.join(("http://www.youtube.com", link))
youtube_links.add(link)
if len(youtube_links) >= max_per_page:
break
config_pytomo.LOG.info("Found %d related video links for url %s"
% (len(youtube_links), url))
return youtube_links
def get_youtube_links(url, max_per_page):
"Return a set of only Youtube links from url"
if not ('youtube' in url or 'youtu.be' in url):
config_pytomo.LOG.error("Only youtube is implemented, got url: %s" %
url)
return []
links = lib_links_extractor.get_all_links(url)
youtube_links = set()
config_pytomo.LOG.info("Found %d links for url %s" % (len(links), url))
for link in links:
if link.find("/watch") >= 0:
if link.startswith('/'):
link = ''.join(("https://www.youtube.com", link))
youtube_links.add(link)
if len(youtube_links) >= max_per_page:
break
config_pytomo.LOG.info("Found %d related video links for url %s" %
(len(youtube_links), url))
return youtube_links
def get_popular_links(input_time=config_pytomo.TIME_FRAME,
max_results=config_pytomo.MAX_PER_PAGE,
country=GLOBAL_COUNTRY):
'''Returns the most popular youtube links (world-wide).
The number of videos returned is given as Total_pages.
(The results returned are in no particular order).
A set of only Youtube links from url
'''
config_pytomo.LOG.debug('Getting popular links')
if not country:
country = GLOBAL_COUNTRY
time_frame = get_time_frame(input_time)
if max_results > MAX_VIDEO_PER_PAGE:
pages = int(max_results) / MAX_VIDEO_PER_PAGE
else:
pages = 1
for page in xrange(pages):
url = CHARTS_URL.format(country=country,
time_frame=time_frame,
page=(page + 1))
links = lib_links_extractor.get_all_links(url)
if not links:
config_pytomo.LOG.warning('No popular link was found')
popular_links = set()
matcher = re.compile(LINK_REG_EXP)
for link in links:
config_pytomo.LOG.debug('found link: %s' % link)
if link.find(r'/watch?v=') >= 0:
if link.startswith('/'):
link = ''.join(("http://www.youtube.com", link))
popular_links.add(link)
if len(popular_links) >= max_results:
break
if matcher.search(link) >= 0:
config_pytomo.LOG.debug('videos_ids input link: %s' % link)
video_links = parse_watch_videos_link(link)
for video_link in video_links:
popular_links.add(video_link)
if len(popular_links) >= max_results:
break
config_pytomo.LOG.debug('popular links are: %s' % popular_links)
return popular_links
def get_popular_links(input_time=config_pytomo.TIME_FRAME,
max_results=config_pytomo.MAX_PER_PAGE,
country=GLOBAL_COUNTRY):
'''Returns the most popular youtube links (world-wide).
The number of videos returned is given as Total_pages.
(The results returned are in no particular order).
A set of only Youtube links from url
'''
config_pytomo.LOG.debug('Getting popular links')
if not country:
country = GLOBAL_COUNTRY
time_frame = get_time_frame(input_time)
if max_results > MAX_VIDEO_PER_PAGE:
pages = int(max_results) / MAX_VIDEO_PER_PAGE
else:
pages = 1
for page in xrange(pages):
url = CHARTS_URL.format(country=country, time_frame=time_frame,
page=(page + 1))
links = lib_links_extractor.get_all_links(url)
if not links:
config_pytomo.LOG.warning('No popular link was found')
popular_links = set()
matcher = re.compile(LINK_REG_EXP)
for link in links:
config_pytomo.LOG.debug('found link: %s' % link)
if link.find(r'/watch?v=') >= 0:
if link.startswith('/'):
link = ''.join(("http://www.youtube.com", link))
popular_links.add(link)
if len(popular_links) >= max_results:
break
if matcher.search(link) >= 0:
config_pytomo.LOG.debug('videos_ids input link: %s' % link)
video_links = parse_watch_videos_link(link)
for video_link in video_links:
popular_links.add(video_link)
if len(popular_links) >= max_results:
break
config_pytomo.LOG.debug('popular links are: %s' % popular_links)
return popular_links
