Skip to content

Commit 5ad7a8b

Browse files
honzajavorekhonzajavorek
committed
fix: avoid the yes option, fix crawlee installation, improve readability of uv options
1 parent b432ce1 commit 5ad7a8b

File tree

2 files changed

+36
-39
lines changed
  • sources/academy/webscraping

2 files changed

+36
-39
lines changed

‎sources/academy/webscraping/scraping_basics_javascript/exercises/test.bats‎

Lines changed: 19 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -1,112 +1,111 @@
11
setup() {
22
cd "$BATS_TEST_DIRNAME"
3+
export npm_config_yes=true
34
}
45

56
@test "outputs the HTML with Star Wars products" {
6-
run npx --yes node lego.mjs
7+
run npx node lego.mjs
78
[[ "$output" == *"Millennium Falcon"* ]]
89
}
910

1011
@test "counts the number of F1 Academy teams" {
11-
run npx --yes --package=cheerio node f1academy_teams.mjs
12+
run npx --package=cheerio node f1academy_teams.mjs
1213
(( status == 0 ))
1314
[[ -n "$output" ]]
1415
}
1516

1617
@test "counts the number of F1 Academy drivers" {
17-
run npx --yes --package=cheerio node f1academy_drivers.mjs
18+
run npx --package=cheerio node f1academy_drivers.mjs
1819
(( status == 0 ))
1920
[[ -n "$output" ]]
2021
}
2122

2223
@test "lists African countries" {
23-
run npx --yes --package=cheerio node wikipedia_countries.mjs
24+
run npx --package=cheerio node wikipedia_countries.mjs
2425
(( status == 0 ))
2526
[[ -n "$output" ]]
2627
}
2728

2829
@test "lists African countries with a single selector" {
29-
run npx --yes --package=cheerio node wikipedia_countries_single_selector.mjs
30+
run npx --package=cheerio node wikipedia_countries_single_selector.mjs
3031
(( status == 0 ))
3132
[[ -n "$output" ]]
3233
}
3334

3435
@test "lists Guardian F1 article titles" {
35-
run npx --yes --package=cheerio node guardian_f1_titles.mjs
36+
run npx --package=cheerio node guardian_f1_titles.mjs
3637
(( status == 0 ))
3738
[[ -n "$output" ]]
3839
}
3940

4041
@test "prints warehouse stock counts" {
41-
run npx --yes --package=cheerio node warehouse_units.mjs
42+
run npx --package=cheerio node warehouse_units.mjs
4243
(( status == 0 ))
4344
[[ -n "$output" ]]
4445
}
4546

4647
@test "prints warehouse stock counts using regex" {
47-
run npx --yes --package=cheerio node warehouse_units_regex.mjs
48+
run npx --package=cheerio node warehouse_units_regex.mjs
4849
(( status == 0 ))
4950
[[ -n "$output" ]]
5051
}
5152

5253
@test "prints Guardian F1 titles with publish dates" {
53-
run npx --yes --package=cheerio node guardian_publish_dates.mjs
54+
run npx --package=cheerio node guardian_publish_dates.mjs
5455
(( status == 0 ))
5556
[[ -n "$output" ]]
5657
}
5758

5859
@test "filters products from JSON" {
59-
run npx --yes node process_products_json.mjs
60+
run npx node process_products_json.mjs
6061
(( status == 0 ))
6162
[[ -n "$output" ]]
6263
}
6364

6465
@test "lists Wikipedia country links" {
65-
run npx --yes --package=cheerio node wikipedia_country_links.mjs
66+
run npx --package=cheerio node wikipedia_country_links.mjs
6667
(( status == 0 ))
6768
[[ -n "$output" ]]
6869
}
6970

7071
@test "lists Guardian F1 article links" {
71-
run npx --yes --package=cheerio node guardian_f1_links.mjs
72+
run npx --package=cheerio node guardian_f1_links.mjs
7273
(( status == 0 ))
7374
[[ -n "$output" ]]
7475
}
7576

7677
@test "prints Wikipedia calling codes" {
77-
run npx --yes --package=cheerio node wikipedia_calling_codes.mjs
78+
run npx --package=cheerio node wikipedia_calling_codes.mjs
7879
(( status == 0 ))
7980
[[ -n "$output" ]]
8081
}
8182

8283
@test "lists Guardian F1 authors" {
83-
run npx --yes --package=cheerio node guardian_f1_authors.mjs
84+
run npx --package=cheerio node guardian_f1_authors.mjs
8485
(( status == 0 ))
8586
[[ -n "$output" ]]
8687
}
8788

8889
@test "lists npm LLM packages" {
89-
run npx --yes --package=cheerio node npm_llm_packages.mjs
90+
run npx --package=cheerio node npm_llm_packages.mjs
9091
(( status == 0 ))
9192
[[ -n "$output" ]]
9293
}
9394

9495
@test "finds the shortest CNN sports article" {
95-
run npx --yes --package=cheerio node cnn_sports_shortest_article.mjs
96+
run npx --package=cheerio node cnn_sports_shortest_article.mjs
9697
(( status == 0 ))
9798
[[ -n "$output" ]]
9899
}
99100

100101
@test "scrapes F1 Academy driver details with Crawlee" {
101-
run npx --yes --package=crawlee --package=cheerio node crawlee_f1_drivers.mjs
102-
(( status == 0 ))
102+
run npx --package=crawlee node crawlee_f1_drivers.mjs
103103
[[ -n "$output" || -f dataset.json ]]
104104
rm -f dataset.json
105105
}
106106

107107
@test "scrapes Netflix ratings with Crawlee" {
108-
run npx --yes --package=crawlee --package=cheerio node crawlee_netflix_ratings.mjs
109-
(( status == 0 ))
108+
run npx --package=crawlee node crawlee_netflix_ratings.mjs
110109
[[ -n "$output" || -f dataset.json ]]
111110
rm -f dataset.json
112111
}

‎sources/academy/webscraping/scraping_basics_python/exercises/test.bats‎

Lines changed: 17 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -3,54 +3,54 @@ setup() {
33
}
44

55
@test "outputs the HTML with Star Wars products" {
6-
run uv run --with httpx python lego.py
6+
run uv run --with=httpx python lego.py
77
[[ "$output" == *"Millennium Falcon"* ]]
88
}
99

1010
@test "counts the number of F1 Academy teams" {
11-
run uv run --with httpx --with beautifulsoup4 python f1academy_teams.py
11+
run uv run --with=httpx --with=beautifulsoup4 python f1academy_teams.py
1212
(( status == 0 ))
1313
[[ -n "$output" ]]
1414
}
1515

1616
@test "counts the number of F1 Academy drivers" {
17-
run uv run --with httpx --with beautifulsoup4 python f1academy_drivers.py
17+
run uv run --with=httpx --with=beautifulsoup4 python f1academy_drivers.py
1818
(( status == 0 ))
1919
[[ -n "$output" ]]
2020
}
2121

2222
@test "lists African countries" {
23-
run uv run --with httpx --with beautifulsoup4 python wikipedia_countries.py
23+
run uv run --with=httpx --with=beautifulsoup4 python wikipedia_countries.py
2424
(( status == 0 ))
2525
[[ -n "$output" ]]
2626
}
2727

2828
@test "lists African countries with a single selector" {
29-
run uv run --with httpx --with beautifulsoup4 python wikipedia_countries_single_selector.py
29+
run uv run --with=httpx --with=beautifulsoup4 python wikipedia_countries_single_selector.py
3030
(( status == 0 ))
3131
[[ -n "$output" ]]
3232
}
3333

3434
@test "lists Guardian F1 article titles" {
35-
run uv run --with httpx --with beautifulsoup4 python guardian_f1_titles.py
35+
run uv run --with=httpx --with=beautifulsoup4 python guardian_f1_titles.py
3636
(( status == 0 ))
3737
[[ -n "$output" ]]
3838
}
3939

4040
@test "prints warehouse stock counts" {
41-
run uv run --with httpx --with beautifulsoup4 python warehouse_units.py
41+
run uv run --with=httpx --with=beautifulsoup4 python warehouse_units.py
4242
(( status == 0 ))
4343
[[ -n "$output" ]]
4444
}
4545

4646
@test "prints warehouse stock counts using regex" {
47-
run uv run --with httpx --with beautifulsoup4 python warehouse_units_regex.py
47+
run uv run --with=httpx --with=beautifulsoup4 python warehouse_units_regex.py
4848
(( status == 0 ))
4949
[[ -n "$output" ]]
5050
}
5151

5252
@test "prints Guardian F1 titles with publish dates" {
53-
run uv run --with httpx --with beautifulsoup4 python guardian_publish_dates.py
53+
run uv run --with=httpx --with=beautifulsoup4 python guardian_publish_dates.py
5454
(( status == 0 ))
5555
[[ -n "$output" ]]
5656
}
@@ -62,51 +62,49 @@ setup() {
6262
}
6363

6464
@test "lists Wikipedia country links" {
65-
run uv run --with httpx --with beautifulsoup4 python wikipedia_country_links.py
65+
run uv run --with=httpx --with=beautifulsoup4 python wikipedia_country_links.py
6666
(( status == 0 ))
6767
[[ -n "$output" ]]
6868
}
6969

7070
@test "lists Guardian F1 article links" {
71-
run uv run --with httpx --with beautifulsoup4 python guardian_f1_links.py
71+
run uv run --with=httpx --with=beautifulsoup4 python guardian_f1_links.py
7272
(( status == 0 ))
7373
[[ -n "$output" ]]
7474
}
7575

7676
@test "prints Wikipedia calling codes" {
77-
run uv run --with httpx --with beautifulsoup4 python wikipedia_calling_codes.py
77+
run uv run --with=httpx --with=beautifulsoup4 python wikipedia_calling_codes.py
7878
(( status == 0 ))
7979
[[ -n "$output" ]]
8080
}
8181

8282
@test "lists Guardian F1 authors" {
83-
run uv run --with httpx --with beautifulsoup4 python guardian_f1_authors.py
83+
run uv run --with=httpx --with=beautifulsoup4 python guardian_f1_authors.py
8484
(( status == 0 ))
8585
[[ -n "$output" ]]
8686
}
8787

8888
@test "lists Python database jobs" {
89-
run uv run --with httpx --with beautifulsoup4 python python_jobs_database.py
89+
run uv run --with=httpx --with=beautifulsoup4 python python_jobs_database.py
9090
(( status == 0 ))
9191
[[ -n "$output" ]]
9292
}
9393

9494
@test "finds the shortest CNN sports article" {
95-
run uv run --with httpx --with beautifulsoup4 python cnn_sports_shortest_article.py
95+
run uv run --with=httpx --with=beautifulsoup4 python cnn_sports_shortest_article.py
9696
(( status == 0 ))
9797
[[ -n "$output" ]]
9898
}
9999

100100
@test "scrapes F1 Academy driver details with Crawlee" {
101-
run uv run --with httpx --with beautifulsoup4 --with crawlee python crawlee_f1_drivers.py
102-
(( status == 0 ))
101+
run uv run --with=crawlee[beautifulsoup] python crawlee_f1_drivers.py
103102
[[ -n "$output" || -f dataset.json ]]
104103
rm -f dataset.json
105104
}
106105

107106
@test "scrapes Netflix ratings with Crawlee" {
108-
run uv run --with httpx --with beautifulsoup4 --with crawlee python crawlee_netflix_ratings.py
109-
(( status == 0 ))
107+
run uv run --with=crawlee[beautifulsoup] python crawlee_netflix_ratings.py
110108
[[ -n "$output" || -f dataset.json ]]
111109
rm -f dataset.json
112110
}

0 commit comments

Comments
 (0)