def main():
args = parse_args()
# arguments parsing
if not any([args.url, args.album_name]):
logger.error(
"Not enough arguments. Use -h to see available arguments.")
exit()
RymNetwork = rymscraper.RymNetwork(headless=args.no_headless)
logger.info("Extracting album timeline.")
if args.album_name:
album_timeline = RymNetwork.get_album_timeline(name=args.album_name)
elif args.url:
album_timeline = RymNetwork.get_album_timeline(url=args.url)
export_directory = "Exports"
Path(export_directory).mkdir(parents=True, exist_ok=True)
if args.album_name:
export_name = args.album_name
else:
export_name = " - ".join(args.url.split("/")[-3:-1])
export_filename = f"{export_directory}/{int(time.time())}_export_album_timeline_{export_name}.json"
logger.info("Exporting results to %s.", export_filename)
with open(export_filename, "w") as f:
f.write(json.dumps(album_timeline, indent=4, ensure_ascii=False))
RymNetwork.browser.close()
RymNetwork.browser.quit()
logger.debug("Runtime : %.2f seconds." % (time.time() - temps_debut))
def main():
args = parse_args()
# arguments parsing
if not any([args.url, args.artist, args.file_url, args.file_artist]):
logger.error("Not enough arguments. Use -h to see available arguments.")
exit()
list_urls = None
list_artists = None
if args.url:
list_urls = [x.strip() for x in args.url.split(",") if x.strip()]
logger.debug("Option url found, list_urls : %s.", list_urls)
if args.file_url:
try:
with open(args.file_url) as f:
list_urls = [
x.strip()
for x in f.readlines()
if x.strip() and not x.startswith("#")
]
except Exception as e:
logger.error(e)
exit()
logger.debug("Option file_url found, list_urls : %s.", list_urls)
if args.artist:
list_artists = [x.strip() for x in args.artist.split(",") if x.strip()]
logger.debug("Option artist found, list_artists : %s.", list_artists)
if args.file_artist:
try:
with open(args.file_artist) as f:
list_artists = [
x.strip() for x in f if x.strip() and not x.startswith("#")
]
except Exception as e:
logger.error(e)
exit()
logger.debug("Option file_artist found, list_artists : %s.", list_artists)
RymNetwork = rymscraper.RymNetwork(headless=args.no_headless)
logger.info("Extracting artist infos.")
if list_artists:
list_artists_infos = RymNetwork.get_artists_infos(names=list_artists)
elif list_urls:
logger.debug(list_urls)
list_artists_infos = RymNetwork.get_artists_infos(urls=list_urls)
export_directory = "Exports"
Path(export_directory).mkdir(parents=True, exist_ok=True)
export_filename = f"{export_directory}/{int(time.time())}_export_artist"
RymNetwork.browser.close()
RymNetwork.browser.quit()
logger.info("Exporting results to %s.", export_filename + ".csv")
df = pd.DataFrame(list_artists_infos)
df.to_csv(export_filename + ".csv", sep="\t", index=False)
logger.debug("Runtime : %.2f seconds." % (time.time() - temps_debut))
def main():
args = parse_args()
export_directory = "Exports"
Path(export_directory).mkdir(parents=True, exist_ok=True)
if not args.url:
url = RymUrl.RymUrl()
export_filename = f"{export_directory}/{int(time.time())}_export_chart"
logger.debug("rym_url : %s.", url)
if args.everything:
export_filename += f"_everything"
url.url_part_type = f"/release"
else:
export_filename += f"_album"
if args.year:
export_filename += f"_{args.year}"
url.url_part_year = f"/{args.year}"
if args.genre:
export_filename += f"_{args.genre}"
url.url_part_genres = f"/g:{args.genre}"
if args.country:
export_filename += f"_{args.country}"
url.url_part_origin_countries = f"/loc:{args.country}"
else:
url = args.url
export_filename = f"{export_directory}/{int(time.time())}_export_url"
logger.debug("completed rym_url : %s.", url)
RymNetwork = rymscraper.RymNetwork(headless=args.no_headless)
logger.info("Extracting infos from the chart.")
list_rows = RymNetwork.get_chart_infos(url, max_page=args.page)
columns = [
"Rank",
"Artist",
"Album",
"Date",
"Genres",
"RYM Rating",
"Ratings",
"Reviews",
]
df = pd.DataFrame(list_rows)
df = df[columns]
logger.info("Exporting results to %s.", export_filename + ".csv")
df.to_csv(export_filename + ".csv", sep="\t", index=False)
RymNetwork.browser.close()
RymNetwork.browser.quit()
logger.debug("Runtime : %.2f seconds." % (time.time() - temps_debut))
def main():
args = parse_args()
# arguments parsing
if not any([args.url, args.artist, args.file_url, args.file_artist]):
logger.error("Not enough arguments. Use -h to see available arguments.")
exit()
list_artists = None
list_urls = None
if args.url:
list_urls = [x.strip() for x in args.url.split(",") if x.strip()]
logger.debug("Option url found, list_urls : %s.", list_urls)
if args.file_url:
try:
with open(args.file_url) as f:
list_urls = [
x.strip()
for x in f.readlines()
if x.strip() and not x.startswith("#")
]
except Exception as e:
logger.error(e)
exit()
logger.debug("Option file_url found, list_urls : %s.", list_urls)
if args.artist:
list_artists = [x.strip() for x in args.artist.split(",") if x.strip()]
logger.debug("Option artist found, list_artists : %s.", list_artists)
if args.file_artist:
try:
with open(args.file_artist) as f:
list_artists = [
x.strip() for x in f if x.strip() and not x.startswith("#")
]
except Exception as e:
logger.error(e)
exit()
logger.debug("Option file_artist found, list_artists : %s.", list_artists)
# # starting selenium browser
RymNetwork = rymscraper.RymNetwork(headless=args.no_headless)
logger.info("Extracting artist infos.")
if list_artists:
list_artists_disco = RymNetwork.get_discographies_infos(
names=list_artists, complementary_infos=args.complementary_infos
)
elif list_urls:
logger.debug(list_urls)
list_artists_disco = RymNetwork.get_discographies_infos(
urls=list_urls, complementary_infos=args.complementary_infos
)
RymNetwork.browser.close()
RymNetwork.browser.quit()
export_directory = "Exports"
Path(export_directory).mkdir(parents=True, exist_ok=True)
export_filename = f"{export_directory}/{int(time.time())}_export_discography"
# columns = ['Artist',
# 'Name',
# 'URL',
# 'Category',
# 'Type',
# 'Year',
# 'Date',
# 'Average Rating',
# 'Ratings',
# 'Reviews',
# 'Genres',
# 'Language',
# 'Descriptors',
# 'Recorded',
# ]
df = pd.DataFrame.from_records(list_artists_disco)
# reorder columns
# df = df[columns]
logger.info("Exporting results to %s.", export_filename + ".csv")
df.to_csv(export_filename + ".csv", sep="\t", index=False)
logger.debug("Runtime : %.2f seconds." % (time.time() - temps_debut))
def network():
network = rymscraper.RymNetwork(headless=True)
yield network
network.browser.close()
network.browser.quit()