python自动化测试之Playwright使用

1
2
3
4
5
# 安装playwright
pip install playwright
# 安装需要的浏览器驱动，支持chrome，firefox和webkit三种浏览器驱动
python -m playwright install

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
# 演示程序爬取一个网页中表格的全部数据
# 使用同步的API
from playwright.sync_api import sync_playwright
# 用作类型标注，方便IDE提示
from typing import List
from playwright.sync_api import Browser, Page
# 获取表格中的数据
def extract_table_data(page: Page) -> "List[str]":
temp = []
# 选用所有符合条件的元素
for cell in page.query_selector_all("#foreach td"):
# element.textContent函数，获得元素内的文字
temp.append(cell.text_content().strip())
for i in range(9):
for cell in page.query_selector_all(f"#foreach_{i} td"):
temp.append(cell.text_content().strip())
return temp
# 表格有三列，需要把一个列表拆分成三个
def split_lines(origin_list: list, list_len: int) -> List:
return [origin_list[i:i + list_len] for i in range(0, len(origin_list),
list_len)]
def main():
with sync_playwright() as playwright:
# 创建浏览器，使用chrome浏览器，无头模式
browser: Browser = playwright.chromium.launch(headless=True)
# 创建新页面
page: Page = browser.new_page()
page.goto(
"http://femhzs.mofcom.gov.cn/fecpmvc/pages/fem/CorpJWList.html")
# 等待加载完毕，之后截个图
page.wait_for_load_state("networkidle")
page.screenshot(path="./screenshot.jpg", type="jpeg")
# 抽取数据并输出到控制台上
table = extract_table_data(page)
line: List[str]
for line in split_lines(table, 3):
print(line[0] + "-" + line[1] + "-" + line[2])
# 关闭浏览器
browser.close()
if __name__ == "__main__":
main()

1
2
3
# 访问维基百科然后录制脚本
playwright codegen wikipedia.org