Created
May 15, 2024 14:17
-
-
Save jianghu52/c52c92ea56273799a77450a0ad0e0ff2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#读取本地E:\python_pro\本地脚本\sample.html文件,并将其中的表格数据提取出来 | |
import pandas as pd | |
from bs4 import BeautifulSoup | |
import json | |
# 定义一个结构体类 | |
class Struct: | |
def __init__(self, link, target, imgPath, before_p, after_p): | |
self.link = link | |
self.target = target | |
self.imgPath = imgPath | |
self.before_p = before_p | |
self.after_p = after_p | |
#定义一个td结构体类 | |
class TdStruct: | |
def __init__(self, tdvalues,thValue): | |
self.tdvalues = tdvalues | |
self.thValue = thValue | |
max_td = 0 | |
max_tr = 0 | |
def get_tds(htmlpath): | |
#读取本地文件 | |
with open(htmlpath, 'r', encoding='utf-8') as f: | |
html = f.read() | |
#解析html | |
soup = BeautifulSoup(html, 'html.parser') | |
#取得table里的tbody数据 | |
tbody = soup.find('table').find('tbody') | |
#获取最大tr数 | |
max_tr = len(tbody.find_all('tr')) | |
#获取一行的最大td数 | |
max_td = len(tbody.find_all('td')) | |
print('max_tr:', max_tr) | |
print('max_td:', max_td) | |
#便利tbody里的tr标签,取得每一行的td标签数据 | |
td_list = [] | |
for tr in tbody.find_all('tr'): | |
th = tr.find('th').contents | |
thvalue = ''.join(str(item) for item in th) | |
tdvalues = [] | |
for td in tr.find_all('td'): | |
tdvalue = ''.join(str(item) for item in td.contents) | |
tdvalues.append(tdvalue) | |
td_list.append(TdStruct(tdvalues,thvalue)) | |
return td_list | |
def get_th_json(htmlpath): | |
#读取本地文件 | |
with open(htmlpath, 'r', encoding='utf-8') as f: | |
html = f.read() | |
#解析html | |
soup = BeautifulSoup(html, 'html.parser') | |
#取得table里的thead数据 | |
thead = soup.find('table').find('thead') | |
#便利thead里的tr标签,取得每一行的th标签数据 | |
th_list = [] | |
data_value_list = [] | |
for th in thead.find_all('th'): | |
target = '' | |
link = th.find('a') | |
if link: | |
link = link.get('href') | |
target = th.find('a').get('target') | |
else: | |
link = '' | |
imgPath = th.find('img') | |
if imgPath: | |
imgPath = imgPath.get('src') | |
else: | |
imgPath = '' | |
pstring = th.find('p') | |
before_p = '' | |
after_p = '' | |
if pstring: | |
content = ''.join(str(item) for item in pstring.contents) | |
#将<p>标签内的内容转换为字符串 | |
if '<br/>' in content: | |
before_p, after_p = content.split('<br/>', 1) # 使用split方法按照<br/>进行分割 | |
else: | |
before_p = content | |
after_p = '' | |
else: | |
pstring = '' | |
th_list.append(Struct(link, target, imgPath, before_p, after_p)) | |
data_value_list.append(str( th.get('data-selection-value'))) | |
tdlist = get_tds(htmlpath) | |
# 构建JSON对象 | |
json_obj = { | |
'thvalues': [] | |
} | |
# 将th_list结果追加到JSON对象中 | |
for i in range(len(th_list)): | |
json_obj['thvalues'].append({ | |
'link': th_list[i].link, | |
'target': th_list[i].target, | |
'imgPath': th_list[i].imgPath, | |
'before_p': th_list[i].before_p, | |
'after_p': th_list[i].after_p, | |
'data_value': data_value_list[i], | |
'thvalue': tdlist[i].thValue, | |
#循环追加tdvalues | |
'tdvalues': [] | |
}) | |
for j in range(21): | |
print('j is:', j) | |
print('i is==',i) | |
json_obj['thvalues'][i]['tdvalues'].append({ | |
tdlist[j].thValue: tdlist[j].tdvalues[i-1] | |
}) | |
# 输出JSON对象 | |
#print(json.dumps(json_obj, ensure_ascii=False)) | |
# 保存JSON对象到文件 | |
with open(htmlpath.replace('.html', '.json'), 'w', encoding='utf-8') as f: | |
json.dump(json_obj, f, ensure_ascii=False) | |
get_th_json('E:\python_pro\本地脚本\sample.html') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment