1 pip install playwright

1 python -m playwright install

 1 import time,re
 2 
 3 from playwright.sync_api import Playwright, sync_playwright, expect
 4 
 5 def cancel_request(route,request):
 6     route.abort()
 7 def run(playwright: Playwright) -> None:
 8     browser = playwright.chromium.launch(headless=False)
 9     context = browser.new_context()
10     page = context.new_page()
11     # 不加載圖片
12     # page.route(re.compile(r"(\.png)|(\.jpg)"), cancel_request)
13     page.goto("https://mobinovels.com/")
14     # 由于魔筆小說首頁是動態(tài)加載列表，因此在此處加30s延遲，需手動滑動頁面至底部直至加載完全部內(nèi)容
15     for i in range(30):
16         time.sleep(1)
17         print(i)
18     # 定位至列表元素
19     novel_list = page.locator('[class="post-title entry-title"]')
20     # 統(tǒng)計(jì)小說數(shù)量
21     total = novel_list.count()
22     # 遍歷獲取小說詳情地址
23     for i in range(total):
24         novel = novel_list.nth(i).locator("a")
25         title = novel.inner_text()
26         title_url = novel.get_attribute("href")
27         page1 = context.new_page()
28         page1.goto(title_url,wait_until='domcontentloaded')
29         print(i+1,total,title)
30         try:
31             content_list = page1.locator("table>tbody>tr")
32             # 保存至單獨(dú)txt文件中供后續(xù)下載
33             with open('./novelurl/'+title+'.txt', 'a') as f:
34                 for j in range(content_list.count()):
35                     if content_list.nth(j).locator("td").count() > 2:
36                         content_href = content_list.nth(j).locator("td").nth(3).locator("a").get_attribute("href")
37                         f.write(title+str(j+1)+'分割'+content_href + '\n')
38         except:
39             pass
40         page1.close()
41     # 程序結(jié)束后手動關(guān)閉程序
42     time.sleep(50000)
43     page.close()
44 
45     # ---------------------
46     context.close()
47     browser.close()
48 
49 
50 with sync_playwright() as playwright:
51     run(playwright)

 1                         if "t00y.com" in new_url:
 2                             page.goto(new_url)
 3                         elif "?p=6195" not in new_url:
 4                             page.goto(new_url+"?p=6195")
 5                             page.get_by_placeholder("文件訪問密碼").click()
 6                             page.get_by_role("button", name="解密文件").click()
 7                         else:
 8                             page.goto(new_url)
 9                             page.get_by_placeholder("文件訪問密碼").click()
10                             page.get_by_role("button", name="解密文件").click()

 1 import time,os
 2 
 3 from playwright.sync_api import Playwright, sync_playwright, expect
 4 
 5 
 6 def run(playwright: Playwright) -> None:
 7     browser = playwright.chromium.launch(channel="chrome", headless=False) # 此處使用的是本地chrome瀏覽器
 8     context = browser.new_context()
 9     path = r'D:\PycharmProjects\wxauto\novelurl'
10     dir_list = os.listdir(path)
11     # 使用cookies
12     # cookies = []
13     # context.add_cookies(cookies)
14     page = context.new_page()
15     for i in range(len(dir_list)):
16         try:
17             novel_url = os.path.join(path, dir_list[i])
18             print(novel_url)
19             with open(novel_url) as f:
20                     for j in f.readlines():
21                         new_name,new_url = j.strip().split("分割")
22                         if "t00y.com" in new_url:
23                             page.goto(new_url)
24                         elif "?p=6195" not in new_url:
25                             page.goto(new_url+"?p=6195")
26                             page.get_by_placeholder("文件訪問密碼").click()
27                             page.get_by_role("button", name="解密文件").click()
28                         else:
29                             page.goto(new_url)
30                             page.get_by_placeholder("文件訪問密碼").click()
31                             page.get_by_role("button", name="解密文件").click()
32 
33                         with page.expect_download(timeout=100000) as download_info:
34                             page.get_by_role("button", name="立即下載").first.click()
35                             print(new_name,"開始下載")
36                         download_file = download_info.value
37                         download_file.save_as("./novel/"+dir_list[i][:-4]+"/"+download_file.suggested_filename)
38                         time.sleep(3)
39             os.remove(novel_url)
40             print(i+1,dir_list[i],"下載結(jié)束")
41         except:
42             print(novel_url,"出錯")
43     time.sleep(60)
44     page.close()
45 
46     # ---------------------
47     context.close()
48     browser.close()
49 
50 
51 with sync_playwright() as playwright:
52     run(playwright)