281 lines
9.7 KiB
Python
Executable File
281 lines
9.7 KiB
Python
Executable File
# coding=utf-8
|
|
import json
|
|
import time
|
|
import random
|
|
import sys
|
|
import os
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
import traceback
|
|
from selenium.webdriver.common.by import By
|
|
from selenium.webdriver.support.ui import WebDriverWait
|
|
from selenium.webdriver.support import expected_conditions as EC
|
|
from selenium.common.exceptions import TimeoutException, NoSuchWindowException, WebDriverException
|
|
from selenium.webdriver.common.action_chains import ActionChains
|
|
from config import create_browser,_scroll_into_view
|
|
def find_valid_detail_tab(driver, origin_handle, timeout=10):
|
|
"""从现有句柄中挑出一个不是原始窗口的有效新标签页。"""
|
|
end_time = time.time() + timeout
|
|
while time.time() < end_time:
|
|
for handle in driver.window_handles:
|
|
if handle != origin_handle:
|
|
try:
|
|
driver.switch_to.window(handle)
|
|
current_url = driver.current_url
|
|
if not current_url.startswith("chrome://") and current_url != "about:blank":
|
|
print(f"[维普切换窗口] 成功 → {driver.title}")
|
|
return handle
|
|
except Exception:
|
|
pass
|
|
time.sleep(0.5)
|
|
raise Exception("未能在规定时间内找到有效详情页窗口")
|
|
# ---------主函数 ---------
|
|
def extract_row_info(row, driver):
|
|
"""抓取单条记录信息并返回字典"""
|
|
|
|
try:
|
|
type_text = row.find_element(By.XPATH, 'td[5]/div/span').text.strip()
|
|
except Exception:
|
|
type_text = ""
|
|
# 如果不是期刊论文，直接跳过
|
|
if type_text != "期刊论文":
|
|
return None
|
|
|
|
try:
|
|
title_element = row.find_element(By.XPATH, 'td[2]/div/div/a')
|
|
title = title_element.text.strip()
|
|
print("论文名称:", title)
|
|
except Exception:
|
|
print("[错误] 标题元素未找到")
|
|
return None
|
|
|
|
try:
|
|
author_elems = row.find_elements(
|
|
By.XPATH,
|
|
".//div[contains(@class,'six-wrap')]//*[@data-warden-event-id='author-click']"
|
|
)
|
|
authors = [e.text.strip() for e in author_elems if e.text.strip()]
|
|
except Exception:
|
|
authors = []
|
|
print("作者列表:", authors)
|
|
|
|
try:
|
|
source = row.find_element(By.XPATH, "td[4]/div/a").text
|
|
except Exception:
|
|
source = ""
|
|
print("期刊来源:", source)
|
|
print("类型:", type_text)
|
|
|
|
time.sleep(1)
|
|
try:
|
|
origin = driver.current_window_handle
|
|
except NoSuchWindowException:
|
|
print("[错误] 当前窗口不存在")
|
|
return None
|
|
|
|
existing_handles = driver.window_handles
|
|
# 点击标题打开新窗口
|
|
clicked = False
|
|
try:
|
|
_scroll_into_view(driver, title_element)
|
|
title_element.click()
|
|
clicked = True
|
|
except Exception:
|
|
try:
|
|
ActionChains(driver).move_to_element(title_element).pause(1).click(title_element).perform()
|
|
clicked = True
|
|
except Exception:
|
|
try:
|
|
driver.execute_script("arguments[0].click();", title_element)
|
|
clicked = True
|
|
except Exception:
|
|
print("[错误] 点击标题失败")
|
|
clicked = False
|
|
|
|
if not clicked:
|
|
return None
|
|
|
|
try:
|
|
WebDriverWait(driver, 10).until(EC.new_window_is_opened(existing_handles))
|
|
except TimeoutException:
|
|
print("[警告] 未检测到新窗口，跳过")
|
|
return None
|
|
|
|
try:
|
|
# 获取新窗口句柄
|
|
new_handles = driver.window_handles
|
|
detail_tab = next((h for h in new_handles if h != origin), None)
|
|
if not detail_tab:
|
|
print("[警告] 找不到新窗口")
|
|
return None
|
|
|
|
driver.switch_to.window(detail_tab)
|
|
time.sleep(1)
|
|
|
|
try:
|
|
originalLink = driver.current_url
|
|
print("详情页链接:", originalLink)
|
|
except NoSuchWindowException:
|
|
print("[错误] 新窗口已关闭")
|
|
return None
|
|
|
|
# 获取摘要
|
|
summary_text = ""
|
|
try:
|
|
abstract_elems = driver.find_elements(By.CSS_SELECTOR, "span.ellipsis.content-text")
|
|
if abstract_elems:
|
|
summary_text = abstract_elems[0].text.strip()
|
|
else:
|
|
print("[警告] 摘要信息未找到")
|
|
except Exception:
|
|
summary_text = ""
|
|
print("摘要:", summary_text)
|
|
|
|
# 获取关键词
|
|
keywords = []
|
|
try:
|
|
keyword_container = driver.find_element(By.XPATH, "//div[contains(., '关键词')]")
|
|
keyword_spans = keyword_container.find_elements(By.CSS_SELECTOR, "span.select_hover.pointer span")
|
|
keywords = [k.text.strip() for k in keyword_spans if k.text.strip()]
|
|
except Exception:
|
|
keywords = []
|
|
print("关键词列表:", keywords)
|
|
|
|
time.sleep(1)
|
|
|
|
except (NoSuchWindowException, WebDriverException):
|
|
print("[警告] 窗口操作失败")
|
|
return None
|
|
|
|
finally:
|
|
# 安全关闭新窗口
|
|
try:
|
|
if driver.current_window_handle != origin:
|
|
driver.close()
|
|
driver.switch_to.window(origin)
|
|
time.sleep(random.uniform(0.5, 1.0))
|
|
except (NoSuchWindowException, WebDriverException):
|
|
print("[警告] 无法切回原窗口")
|
|
|
|
return {
|
|
"title": title,
|
|
"author": authors,
|
|
"source": source,
|
|
"site":"维普",
|
|
"keywords": keywords,
|
|
"originalLink": originalLink if 'originalLink' in locals() else "",
|
|
"summary": summary_text
|
|
}
|
|
def crawl_current_sort(driver, limit):
|
|
"""抓取当前排序下的 limit 条记录"""
|
|
fetched_count = 0
|
|
results = []
|
|
|
|
while fetched_count < limit:
|
|
try:
|
|
WebDriverWait(driver, 10).until(
|
|
EC.presence_of_element_located((By.CSS_SELECTOR, '#search_container > div.s-list > div.yx-start.content.al-str'))
|
|
)
|
|
except TimeoutException:
|
|
print("[警告] 本页结果表格未出现，尝试继续")
|
|
time.sleep(2)
|
|
|
|
rows = driver.find_elements(By.XPATH, '//*[@id="search_container"]/div[2]/div[2]/div/div/div[3]/table/tbody/tr')
|
|
|
|
|
|
for row in rows:
|
|
if fetched_count >= limit:
|
|
break
|
|
try:
|
|
info = extract_row_info(row, driver)
|
|
if info:
|
|
results.append(info)
|
|
time.sleep(2)
|
|
fetched_count += 1
|
|
|
|
except Exception as e:
|
|
print(f"[错误] {e}")
|
|
traceback.print_exc()
|
|
try:
|
|
if driver.window_handles:
|
|
driver.switch_to.window(driver.window_handles[0])
|
|
except Exception:
|
|
pass
|
|
|
|
# 翻页
|
|
try:
|
|
next_btn = driver.find_element(By.CSS_SELECTOR, "i.el-icon-arrow-right.pointer")
|
|
|
|
if not next_btn.is_enabled() or fetched_count >= limit:
|
|
break
|
|
_scroll_into_view(driver, next_btn)
|
|
try:
|
|
next_btn.click()
|
|
except Exception:
|
|
try:
|
|
ActionChains(driver).move_to_element(next_btn).pause(0.1).click(next_btn).perform()
|
|
except Exception:
|
|
driver.execute_script("arguments[0].click();", next_btn)
|
|
time.sleep(5)
|
|
except Exception:
|
|
print("[INFO] 已到最后一页或翻页失败")
|
|
break
|
|
|
|
return results
|
|
def weipu(keyword, limit,sort_options=None):
|
|
"""主函数：三种排序抓取"""
|
|
driver = create_browser()
|
|
wait = WebDriverWait(driver, 15)
|
|
all_results = {}
|
|
if not sort_options:
|
|
sort_options = ["relevance"] # 默认相关性
|
|
try:
|
|
driver.get("https://www.cqvip.com/")
|
|
search_input = driver.find_element(By.XPATH, "//input[@placeholder='请输入检索词']")
|
|
search_input.send_keys(keyword)
|
|
time.sleep(2)
|
|
search_button = driver.find_element(By.XPATH, "//button[.//span[contains(text(),'检索')]]")
|
|
search_button.click()
|
|
time.sleep(3)
|
|
#切换展示模式
|
|
element = WebDriverWait(driver, 10).until(
|
|
EC.element_to_be_clickable(
|
|
(By.CSS_SELECTOR, 'i[data-warden-event-id="list-arrange"]')
|
|
)
|
|
)
|
|
driver.execute_script("arguments[0].scrollIntoView({block: 'center'});", element)
|
|
time.sleep(2)
|
|
element.click()
|
|
time.sleep(2)
|
|
for sort_name in sort_options:
|
|
if sort_name == "relevance":
|
|
print("[INFO] 使用相关性排序（默认）")
|
|
elif sort_name == "download_count":
|
|
print("[INFO] 使用被引量排序")
|
|
try:
|
|
driver.find_element(By.XPATH, '//span[contains(text(),"被引量")]').click()
|
|
except Exception:
|
|
print(f"[WARN] 点击排序 {sort_name} 失败")
|
|
elif sort_name == "publication_time":
|
|
print("[INFO] 使用时间排序")
|
|
try:
|
|
driver.find_element(By.XPATH, '//span[contains(text(),"时效性")]').click()
|
|
except Exception:
|
|
print(f"[WARN] 点击排序 {sort_name} 失败")
|
|
time.sleep(1)
|
|
results = crawl_current_sort(driver, limit)
|
|
all_results[sort_name] = results
|
|
finally:
|
|
try:
|
|
driver.quit()
|
|
except Exception:
|
|
pass
|
|
print("[DONE] PDF处理完成")
|
|
print(json.dumps(all_results, ensure_ascii=False, indent=2))
|
|
|
|
return all_results
|
|
|
|
if __name__ == '__main__':
|
|
keyword = "深度学习"
|
|
limit=10
|
|
weipu(keyword,limit,["relevance"])
|