Skip to content

Sourcery Starbot ⭐ refactored cwerner/fastclass #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SourceryAI wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Sourcery Starbot ⭐ refactored cwerner/fastclass #33

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
60 changes: 30 additions & 30 deletions fastclass/fc_download.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,27 +66,22 @@ def crawl(

for c in crawlers:
print(f" -> {c}")
if c == "GOOGLE":
google_crawler = GoogleImageCrawler(
if c == "BAIDU":
baidu_crawler = BaiduImageCrawler(
downloader_cls=CustomDownloader,
parser_cls=GoogleParser,
log_level=logging.CRITICAL,
feeder_threads=1,
parser_threads=1,
downloader_threads=4,
storage={"root_dir": folder},
)

google_crawler.crawl(
baidu_crawler.crawl(
keyword=search,
offset=0,
max_num=maxnum,
min_size=(200, 200),
max_size=None,
file_idx_offset=0,
file_idx_offset="auto",
)

if c == "BING":
elif c == "BING":
bing_crawler = BingImageCrawler(
downloader_cls=CustomDownloader,
log_level=logging.CRITICAL,
Expand All @@ -101,22 +96,7 @@ def crawl(
file_idx_offset="auto",
)

if c == "BAIDU":
baidu_crawler = BaiduImageCrawler(
downloader_cls=CustomDownloader,
log_level=logging.CRITICAL,
storage={"root_dir": folder},
)
baidu_crawler.crawl(
keyword=search,
offset=0,
max_num=maxnum,
min_size=(200, 200),
max_size=None,
file_idx_offset="auto",
)

if c == "FLICKR":
elif c == "FLICKR":
flick_api_key = os.environ.get("FLICKR_API_KEY")
if not flick_api_key:
print(
Expand All @@ -139,15 +119,32 @@ def crawl(
file_idx_offset="auto",
)

elif c == "GOOGLE":
google_crawler = GoogleImageCrawler(
downloader_cls=CustomDownloader,
parser_cls=GoogleParser,
log_level=logging.CRITICAL,
feeder_threads=1,
parser_threads=1,
downloader_threads=4,
storage={"root_dir": folder},
)

google_crawler.crawl(
keyword=search,
offset=0,
max_num=maxnum,
min_size=(200, 200),
max_size=None,
file_idx_offset=0,
)

return {k: v for k, v in CustomDownloader.registry.items() if k is not None}


def main(
infile: str, size: int, crawler: List[str], keep: bool, maxnum: int, outpath: str
):
SIZE = (size, size)
classes = []

if "ALL" in crawler:
crawler = ["GOOGLE", "BING"]

Expand All @@ -156,7 +153,7 @@ def main(
f'Directory "{outpath}" exists. Would you like to overwrite the directory? [y/n]'
)
choice = input().lower()
while not (choice == "y" or "n"):
while choice != "y" and not "n":
print("Please reply with 'y' or 'n'")
choice = input().lower()
if choice == "y":
Expand All @@ -170,6 +167,8 @@ def main(
print(f"INFO: final dataset will be located in {outpath}")

with tempfile.TemporaryDirectory() as tmp:
classes = []

for lcnt, line in enumerate(infile):
if lcnt > 0:
no_cols = line[:-1].count(",") + 1
Expand All @@ -180,6 +179,7 @@ def main(
remove_terms = None
classes.append((search_term, remove_terms))

SIZE = (size, size)
for i, (search_term, remove_terms) in enumerate(classes):
print(f"[{i+1}/{len(classes)}] Searching: >> {search_term} <<")
out_name = sanitize_searchstring(search_term, rstring=remove_terms)
Expand Down