|
|
@@ -94,40 +94,40 @@ class ShipinhaoRecommend:
|
|
|
pass
|
|
|
|
|
|
for i in range(scan_count):
|
|
|
- # try:
|
|
|
- Common.logger(log_type, crawler).info(f"第{i + 1}条视频")
|
|
|
- Common.logging(log_type, crawler, env, f"第{i + 1}条视频")
|
|
|
- if len(driver.find_elements(By.ID, "com.tencent.mm:id/dkf")) != 0:
|
|
|
- Common.logger(log_type, crawler).info("这是一个直播间，滑动至下一个视频\n")
|
|
|
- Common.logging(log_type, crawler, env, "这是一个直播间，滑动至下一个视频\n")
|
|
|
- driver.swipe(10, 1600, 10, 300, 200)
|
|
|
- continue
|
|
|
- video_dict = cls.get_video_info(driver)
|
|
|
- for k, v in video_dict.items():
|
|
|
- Common.logger(log_type, crawler).info(f"{k}:{v}")
|
|
|
- Common.logging(log_type, crawler, env, f"video_dict:{video_dict}")
|
|
|
-
|
|
|
- if video_dict["video_title"] is None:
|
|
|
- Common.logger(log_type, crawler).info("无效视频")
|
|
|
- Common.logging(log_type, crawler, env, "无效视频")
|
|
|
- elif download_rule(log_type=log_type, crawler=crawler, video_dict=video_dict, rule_dict=rule_dict) is False:
|
|
|
- Common.logger(log_type, crawler).info("不满足抓取规则")
|
|
|
- Common.logging(log_type, crawler, env, "不满足抓取规则\n")
|
|
|
- elif cls.repeat_out_video_id(log_type, crawler, video_dict["video_id"], env) != 0:
|
|
|
- Common.logger(log_type, crawler).info('视频已下载')
|
|
|
- Common.logging(log_type, crawler, env, '视频已下载\n')
|
|
|
- else:
|
|
|
- cls.download_video_list.append(video_dict)
|
|
|
- if i+1 == scan_count:
|
|
|
- Common.logger(log_type, crawler).info("扫描一轮结束\n")
|
|
|
- Common.logging(log_type, crawler, env, "扫描一轮结束\n")
|
|
|
- return
|
|
|
- Common.logger(log_type, crawler).info(f"已抓取符合规则视频{len(cls.download_video_list)}条，滑动至下一个视频\n")
|
|
|
- Common.logging(log_type, crawler, env, f"已抓取符合规则视频{len(cls.download_video_list)}条，滑动至下一个视频\n")
|
|
|
+ try:
|
|
|
+ Common.logger(log_type, crawler).info(f"第{i + 1}条视频")
|
|
|
+ Common.logging(log_type, crawler, env, f"第{i + 1}条视频")
|
|
|
+ if len(driver.find_elements(By.ID, "com.tencent.mm:id/dkf")) != 0:
|
|
|
+ Common.logger(log_type, crawler).info("这是一个直播间，滑动至下一个视频\n")
|
|
|
+ Common.logging(log_type, crawler, env, "这是一个直播间，滑动至下一个视频\n")
|
|
|
driver.swipe(10, 1600, 10, 300, 200)
|
|
|
- # except Exception as e:
|
|
|
- # Common.logger(log_type, crawler).info(f"扫描单条视频时异常:{e}\n")
|
|
|
- # Common.logging(log_type, crawler, env, f"扫描单条视频时异常:{e}\n")
|
|
|
+ continue
|
|
|
+ video_dict = cls.get_video_info(driver)
|
|
|
+ for k, v in video_dict.items():
|
|
|
+ Common.logger(log_type, crawler).info(f"{k}:{v}")
|
|
|
+ Common.logging(log_type, crawler, env, f"video_dict:{video_dict}")
|
|
|
+
|
|
|
+ if video_dict["video_title"] is None:
|
|
|
+ Common.logger(log_type, crawler).info("无效视频")
|
|
|
+ Common.logging(log_type, crawler, env, "无效视频")
|
|
|
+ elif download_rule(log_type=log_type, crawler=crawler, video_dict=video_dict, rule_dict=rule_dict) is False:
|
|
|
+ Common.logger(log_type, crawler).info("不满足抓取规则")
|
|
|
+ Common.logging(log_type, crawler, env, "不满足抓取规则\n")
|
|
|
+ elif cls.repeat_out_video_id(log_type, crawler, video_dict["video_id"], env) != 0:
|
|
|
+ Common.logger(log_type, crawler).info('视频已下载')
|
|
|
+ Common.logging(log_type, crawler, env, '视频已下载\n')
|
|
|
+ else:
|
|
|
+ cls.download_video_list.append(video_dict)
|
|
|
+ if i+1 == scan_count:
|
|
|
+ Common.logger(log_type, crawler).info("扫描一轮结束\n")
|
|
|
+ Common.logging(log_type, crawler, env, "扫描一轮结束\n")
|
|
|
+ return
|
|
|
+ Common.logger(log_type, crawler).info(f"已抓取符合规则视频{len(cls.download_video_list)}条，滑动至下一个视频\n")
|
|
|
+ Common.logging(log_type, crawler, env, f"已抓取符合规则视频{len(cls.download_video_list)}条，滑动至下一个视频\n")
|
|
|
+ driver.swipe(10, 1600, 10, 300, 200)
|
|
|
+ except Exception as e:
|
|
|
+ Common.logger(log_type, crawler).info(f"扫描单条视频时异常:{e}\n")
|
|
|
+ Common.logging(log_type, crawler, env, f"扫描单条视频时异常:{e}\n")
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
@@ -146,9 +146,12 @@ class ShipinhaoRecommend:
|
|
|
pause_elements = driver.find_elements(By.ID, "com.tencent.mm:id/gpx")
|
|
|
if len(pause_elements) != 0:
|
|
|
pause_elements[0].click()
|
|
|
- duration_str = driver.find_element(By.ID, "com.tencent.mm:id/l7i").text
|
|
|
- duration = int(duration_str.split(":")[0]) * 60 + int(duration_str.split(":")[-1])
|
|
|
- break
|
|
|
+ try:
|
|
|
+ duration_str = driver.find_element(By.ID, "com.tencent.mm:id/l7i").text
|
|
|
+ duration = int(duration_str.split(":")[0]) * 60 + int(duration_str.split(":")[-1])
|
|
|
+ break
|
|
|
+ except NoSuchElementException:
|
|
|
+ duration = 0
|
|
|
else:
|
|
|
duration = 0
|
|
|
|
