def crawler():
browser = Chrome(cache_path=r"E:\temp")
account_list = Utils.io.load_string("huya_account_list.txt")
for account_url in account_list.split("\n"):
browser.get(account_url)
# 读取直播间订阅数量
text_subscribe = ""
try:
label_subscribe = browser.find_element_by_xpath(
'//*[@id="activityCount"]')
if label_subscribe is not None:
text_subscribe = label_subscribe.text
except NoSuchElementException:
pass
# 读取直播间ID
text_id = ""
try:
label_id = browser.find_element_by_css_selector(
'#J_roomHeader > div.room-hd-l > div.host-info > div.host-detail.J_roomHdDetail > span.host-rid'
)
if label_id is not None:
text_id = label_id.text
except NoSuchElementException:
pass
print(account_url, text_id, text_subscribe)
time.sleep(3)
def crawler(live_list_path):
driver = Chrome(cache_path=r"E:\Temp")
account_list = Utils.io.load_string(live_list_path)
for account_url in account_list.split("\n"):
driver.get(account_url)
time.sleep(3)
text_subscribe = ""
for _ in range(10):
try:
label_subscribe = driver.find_element_by_xpath(
'//*[@id="js-player-title"]/div/div[4]/div/span')
if label_subscribe.text is not None and label_subscribe.text != "":
text_subscribe = label_subscribe.text
break
time.sleep(1)
except NoSuchElementException:
time.sleep(1)
print(account_url, text_subscribe)