2
import os
from bs4 import BeautifulSoup
do = dir_with_original_files = 'C:\Users\ADMIN\Desktop\\new_folder'
dm = dir_with_modified_files = 'C:\Users\ADMIN\Desktop\\new_folder\\test'
for root, dirs, files in os.walk(do):
for f in files:
print f.title()
if f.endswith('~'): #you don't want to process backups
continue
original_file = os.path.join(root, f)
mf = f.split('.')
mf = ''.join(mf[:-1])+'_mod.'+mf[-1] # you can keep the same name
# if you omit the last two lines.
# They are in separate directories
# anyway. In that case, mf = f
modified_file = os.path.join(dm, mf)
with open(original_file, 'r') as orig_f, \
open(modified_file, 'w') as modi_f:
soup = BeautifulSoup(orig_f.read())
for t in soup.find_all('td', class_='findThisClass'):
for child in t.find_all("font"):
if child.string is not None:
child.string.wrap(soup.new_tag('h2'))
for t in soup.find_all('table', class_='tableClass'):
t.extract()
# This is where you create your new modified file.
modi_f.write(soup.prettify().encode(soup.original_encoding))
特定屬性選擇標籤此代碼將找到類<td class=findThisClass>
內的所有<font>
標籤和那些字體標籤中添加。在BeautifulSoup/Python的
我想什麼做的是找到與此標記所有的HTML:
<font color="#333333" face="Verdana" size="3" style="font-weight: bold; background-color: rgb(255, 255, 255);">
什麼是這樣做的最好的方式,如果:
(一)我放心,字體將始終遵循相同的形式(在同一順序的所有屬性,按Ctrl + F以該字符串會發現所有的比賽,我想):
<font color="#333333" face="Verdana" size="3" style="font-weight: bold; background-color: rgb(255, 255, 255);">
(B)如果我想即使屬性順序圍繞例如關它的工作:
<font color="#333333" face="Verdana" size="3" style="font-weight: bold; background-color: rgb(255, 255, 255);">
而且還改變
<font face="Verdana" color="#333333" size="3" style="font-weight: bold; background-color: rgb(255, 255, 255);">
非常感謝。