Revision of ncbi_genome_download.sh

1 file changed, 28 insertions

ncbi_genome_download.sh

			@@ -15,4 +15,32 @@ for f in batches/batch_*; do
15	15
16	16		# 关键：主动降速，避免触发 NCBI 限制
17	17		sleep 10
	18	+	done
	19	+
	20	+
	21	+	#!/usr/bin/env bash
	22	+
	23	+	mkdir -p zips genomes
	24	+
	25	+	for f in batches/batch_*; do
	26	+	base=$(basename "$f")
	27	+	out="zips/${base}.zip"
	28	+	dir="genomes/$base"
	29	+
	30	+	# 如果已经有对应解压目录，就认为完成，直接跳过
	31	+	if [[ -d "$dir" ]]; then
	32	+	echo "SKIP (exists): $dir"
	33	+	continue
	34	+	fi
	35	+
	36	+	echo "Downloading $f -> $out"
	37	+	datasets download genome accession --inputfile "$f" \
	38	+	--include genome,gff3,gbff \
	39	+	--filename "$out"
	40	+
	41	+	mkdir -p "$dir"
	42	+	unzip -q "$out" -d "$dir"
	43	+
	44	+	# 主动降速，避免触发 NCBI 限制
	45	+	sleep 10
18	46		done

1 file changed, 2 insertions

ncbi_genome_download.sh

			@@ -1,3 +1,5 @@
	1	+	conda create -n ncbi_dl -y -c conda-forge ncbi-datasets-cli jq
	2	+
1	3		for f in batches/batch_*; do
2	4		base=$(basename "$f")
3	5		out="zips/${base}.zip"

1 file changed, 16 insertions

ncbi_genome_download.sh(file created)

		@@ -0,0 +1,16 @@
1	+	for f in batches/batch_*; do
2	+	base=$(basename "$f")
3	+	out="zips/${base}.zip"
4	+
5	+	echo "Downloading $f -> $out"
6	+	datasets download genome accession --inputfile "$f" \
7	+	--include genome,gff3,gbff \
8	+	--filename "$out"
9	+
10	+	# 解压到独立目录（也可以最后统一解压）
11	+	mkdir -p "genomes/$base"
12	+	unzip -q "$out" -d "genomes/$base"
13	+
14	+	# 关键：主动降速，避免触发 NCBI 限制
15	+	sleep 10
16	+	done

Newer Older