mostm
/
paimon_moe_importing
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix errors parsing fandom banners

This commit is contained in:
Hashblen 2023-12-31 17:37:25 +01:00
parent 826c0fcdcd
commit 29e594769e
1 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
banner_parser.py
View File

@ -24,12 +24,16 @@ def load_page():
def load_page_static(): def load_page_static():
with open('banner_history_wiki\Wish History _ Genshin Impact Wiki _ Fandom.html', 'r') as f: try:
return f.read() with open('banner_history_wiki\Wish History _ Genshin Impact Wiki _ Fandom.html', 'r') as f:
return f.read()
except UnicodeDecodeError as e:
with open('banner_history_wiki\Wish History _ Genshin Impact Wiki _ Fandom.html', 'r', encoding="utf8") as f:
return f.read()
def parse_table(table: Tag): def parse_table(table: Tag):
header = table.find('thead') header = table.find('tbody') # thead doesn't exist for me
header_row = header.find('tr') header_row = header.find('tr')
header_cells = header_row.find_all('th') header_cells = header_row.find_all('th')
header_titles = [x.text.strip() for x in header_cells] header_titles = [x.text.strip() for x in header_cells]
@ -39,7 +43,7 @@ def parse_table(table: Tag):
return None return None
body = table.find('tbody') body = table.find('tbody')
body_rows = body.find_all('tr') body_rows = body.find_all('tr')[1:] # as thead doesn't exist for me, I add [1:]
reset_time = time(hour=5, minute=0, second=0) # UTC+1 == Europe reset_time = time(hour=5, minute=0, second=0) # UTC+1 == Europe
@ -89,7 +93,7 @@ def parse_page(page_text):
results = [] results = []
soup = BeautifulSoup(page_text, 'lxml') soup = BeautifulSoup(page_text, 'lxml')
tables = soup.find_all('table', class_='article-table alternating-colors-table sortable jquery-tablesorter') tables = soup.find_all('table', class_='article-table alternating-colors-table sortable') # jquery-tablesorter is added after opening the page, it doesn't exist when you wget.
for table in tables: for table in tables:
results += parse_table(table) results += parse_table(table)