1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
|
From: YOKOTA Hiroshi <yokota.hgml@gmail.com>
Date: Sun, 19 Feb 2023 12:46:58 +0900
Subject: Use downloaded static file for reproducible build
---
setup/browser_data.py | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/setup/browser_data.py b/setup/browser_data.py
index b119620..25aa488 100644
--- a/setup/browser_data.py
+++ b/setup/browser_data.py
@@ -7,6 +7,7 @@ import os
import sys
from datetime import datetime
from urllib.request import urlopen
+from pathlib import Path
from setup import download_securely
@@ -23,7 +24,8 @@ def filter_ans(ans):
def common_user_agents():
print('Getting recent UAs...')
- raw = download_from_calibre_server('https://code.calibre-ebook.com/ua-popularity')
+ p = Path.cwd() / "debian" / "resources-src" / "recent_uas" / "common_user_agents.bz2"
+ raw = download_from_calibre_server(p.as_uri())
ans = {}
for line in bz2.decompress(raw).decode('utf-8').splitlines():
count, ua = line.partition(':')[::2]
@@ -37,8 +39,9 @@ def common_user_agents():
def firefox_versions():
print('Getting firefox versions...')
import html5lib
+ p = Path.cwd() / "debian" / "resources-src" / "recent_uas" / "firefox_versions.html"
raw = download_securely(
- 'https://www.mozilla.org/en-US/firefox/releases/').decode('utf-8')
+ p.as_uri()).decode('utf-8')
root = html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False)
ol = root.xpath('//main[@id="main-content"]/ol')[0]
ol.xpath('descendant::li/strong/a[@href]')
@@ -51,8 +54,9 @@ def firefox_versions():
def chrome_versions():
print('Getting chrome versions...')
import html5lib
+ p = Path.cwd() / "debian" / "resources-src" / "recent_uas" / "chrome_versions.html"
raw = download_securely(
- 'https://en.wikipedia.org/wiki/Google_Chrome_version_history').decode('utf-8')
+ p.as_uri()).decode('utf-8')
root = html5lib.parse(raw, treebuilder='lxml', namespaceHTMLElements=False)
table = root.xpath('//*[@id="mw-content-text"]//tbody')[-1]
ans = []
|
