67217b614063c0bf07f4b5b69f0705d0125e32b4
angie
  Mon Aug 16 15:31:07 2021 -0700
Wow, 1 million seemed like such a high ceiling once... but GenBank has more than that number of SARS-CoV-2 genomes now\!

diff --git src/hg/utils/otto/sarscov2phylo/searchAllSarsCov2BioSample.sh src/hg/utils/otto/sarscov2phylo/searchAllSarsCov2BioSample.sh
index 10eecb2..6c18a74 100755
--- src/hg/utils/otto/sarscov2phylo/searchAllSarsCov2BioSample.sh
+++ src/hg/utils/otto/sarscov2phylo/searchAllSarsCov2BioSample.sh
@@ -1,19 +1,19 @@
 #!/bin/bash
 
 set -beEu -o pipefail
 
 # Entrez search for all SARS-CoV-2 sequences with length >= 29,000
 # "Severe acute respiratory syndrome coronavirus 2"[Organism] AND ("29000"[SLEN] : "35000"[SLEN])
 query='%22Severe%20acute%20respiratory%20syndrome%20coronavirus%202%22%5BOrganism%5D'
 
 tool=searchAllSarsCov2.sh
 email="$USER%40soe.ucsc.edu"
 
 # Assemble the esearch URL
 base="https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
-url="${base}esearch.fcgi?db=biosample&term=$query&tool=$tool&email=$email&retmax=1000000"
+url="${base}esearch.fcgi?db=biosample&term=$query&tool=$tool&email=$email&retmax=10000000"
 
 curl -s -S "$url" \
 | grep "<Id>" \
 | sed -re 's@\s*<Id>([0-9]+)</Id>@\1@;' \
     > all.biosample.gids.txt