1
import pandas as pd
2
from selenium import webdriver
3
from selenium.webdriver.chrome.service import Service
4
from selenium.webdriver.common.by import By
5
from webdriver_manager.chrome import ChromeDriverManager
6
import re
7
import os
8

9
# 确保目录存在
10
project_directory = "设置为你的路径"
11
if not os.path.exists(project_directory):
12
    os.makedirs(project_directory)
13

14
# 初始化Chrome WebDriver
15
service = Service(ChromeDriverManager().install())
16
driver = webdriver.Chrome(service=service)
17

18
# 初始化一个空的DataFrame来存储所有数据
19
columns = ["DS", "Title", "Consultations requested", "Complainant", "Respondent", "Agreements cited", "Third Parties (original proceedings)"]
20
df = pd.DataFrame(columns=columns)
21

22
try:
23
    # 具体案例ID请在range函数中设置
24
    for case_number in range(1, 645):
25
        url = f"https://www.wto.org/english/tratop_e/dispu_e/cases_e/ds{case_number}_e.htm"
26
        driver.get(url)
27
        driver.implicitly_wait(20)  # 等待页面加载完成
28

29
        # 获取页面的HTML内容
30
        page_source = driver.page_source
31

32
        # 使用正则表达式提取信息
33
        extracted_info = {
34
            "Title": re.search(r"<h1>(.*?)</h1>", page_source, re.DOTALL),
35
            "Consultations requested": re.search(r"<td>.*?Consultations requested.*?</td><td>(.*?)</td>", page_source),
36
            "Complainant": re.search(r"<td>Complainant: </td><td>(.*?)</td>", page_source),
37
            "Respondent": re.search(r"<td>Respondent:</td><td>(.*?)</td>", page_source),
38
            "Agreements cited": re.search(r"<td>Agreements cited:.*?</td><td>(.*?)</td>", page_source, re.DOTALL),
39
            "Third Parties (original proceedings)": re.search(r"<td>Third Parties.*?original proceedings.*?</td><td>(.*?)</td>", page_source)
40
        }
41

42
        # 清理并添加数据到DataFrame
43
        row = {
44
            "DS": f"DS{case_number}",
45
            "Title": re.sub(r'<span class="dsnumber">DS.*?:</span>', '', extracted_info["Title"].group(1)).replace('&nbsp;', ' ') if extracted_info["Title"] else None,
46
            "Consultations requested": extracted_info["Consultations requested"].group(1).replace('&nbsp;', ' ') if extracted_info["Consultations requested"] else None,
47
            "Complainant": extracted_info["Complainant"].group(1).replace('&nbsp;', ' ') if extracted_info["Complainant"] else None,
48
            "Respondent": extracted_info["Respondent"].group(1).replace('&nbsp;', ' ') if extracted_info["Respondent"] else None,
49
            "Agreements cited": re.sub(r'<[^>]+>', '', extracted_info["Agreements cited"].group(1)).replace('&nbsp;', ' ') if extracted_info["Agreements cited"] else None,
50
            "Third Parties (original proceedings)": extracted_info["Third Parties (original proceedings)"].group(1).replace('&nbsp;', ' ') if extracted_info["Third Parties (original proceedings)"] else None
51
        }
52
        df = pd.concat([df, pd.DataFrame([row])], ignore_index=True)
53

54
        # 如果已经处理了10个案例，就停止循环（可选）
55
        # if case_number == 10:
56
        #     break
57

58
finally:
59
    # 关闭浏览器
60
    driver.quit()
61

62
# 保存DataFrame到Excel文件
63
excel_path = os.path.join(project_directory, 'WTO_cases.xlsx')
64
df.to_excel(excel_path, index=False)
65
print(f"Data has been saved to {excel_path}")