import csv
from selenium import webdriver
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, NoSuchElementException
from selenium.webdriver.common.action_chains import ActionChains
driver = ["1", "2"]
colspan = ["1", "2"]
try:
out = open("类目.csv", "w", newline="")
except PermissionError:
print("文件被其他程序占用")
input("")
csv_writer = csv.writer(out, dialect="excel")
csv_writer.writerow(["宝贝ID", "类目"])
def open_chrome():
driver[0] = webdriver.Chrome()
driver[0].get("https://www.dianchacha.com")
input("请登陆后按回车:")
def EC_located(one_group, value):
"""
目的:简化代码长度,参数1选择one或者group切换选中模式
:param value:要找的值【CSS选择器】
:return:选择到的对象
"""
wait = WebDriverWait(driver[0], 10)
if one_group == "one":
try:
ecl = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, value)))
return ecl
except TimeoutException:
print(value, "1元素未加载成功,等待超时")
else:
try:
ecl = wait.until(
EC.presence_of_all_elements_located((By.CSS_SELECTOR, value))
)
return ecl
except TimeoutException:
print(value, "1元素---组---未加载成功,等待超时")
def operating(ID):
先获取ID输入框
driver[0].get("https://www.dianchacha.com/item/info/index/iid/" + ID)
html = driver[0].page_source
if "未能找到亲的宝贝" not in html:
colspans = EC_located("group", ".colspan-1")
colspan[0] = str(colspans[1].text).replace("宝贝类目: ", "")
else:
return operating(ID)
print(colspan)
def writer_txt():
csv_writer.writerow([url[0], colspan[0]])
print("保存", url[0], colspan[0], "成功")
url = ["0", "1"]
def main():
open_chrome()
file = "宝贝ID.txt"
with open(file) as f:
for line in f.readlines():
url[0] = line
print(line)
operating(url[0])
writer_txt()
out.close()
print("已完成")
if name == "main":
main()