spider/EasySpider
1
0
Fork 0
mirror of https://github.com/NaiboWang/EasySpider.git synced 2025-04-22 18:45:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

Linux OCR Hint

Browse Source
This commit is contained in:
Naibo Wang 2023-05-27 20:37:10 +08:00
parent 5853d2da00
commit 914e37aaa6
3 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
ExecuteStage/easyspider_executestage.py
View File

@ -870,11 +870,14 @@ class BrowserThread(Thread):
if sys.platform == "win32": if sys.platform == "win32":
print("要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://blog.csdn.net/u010454030/article/details/80515501\nhttps://www.bilibili.com/video/BV1xz4y1b72D/") print("要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://blog.csdn.net/u010454030/article/details/80515501\nhttps://www.bilibili.com/video/BV1xz4y1b72D/")
elif sys.platform == "darwin": elif sys.platform == "darwin":
print("要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://zhuanlan.zhihu.com/p/146044810") print(e)
print("注意以上错误，要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://zhuanlan.zhihu.com/p/146044810")
elif sys.platform == "linux": elif sys.platform == "linux":
print("要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://zhuanlan.zhihu.com/p/420259031") print(e)
print("注意以上错误，要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://zhuanlan.zhihu.com/p/420259031")
else: else:
print("要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://blog.csdn.net/u010454030/article/details/80515501\nhttps://www.bilibili.com/video/BV1xz4y1b72D/") print(e)
print("注意以上错误，要使用OCR识别功能，你需要安装Tesseract-OCR并将其添加到环境变量PATH中（添加后需重启EasySpider）：https://blog.csdn.net/u010454030/article/details/80515501\nhttps://www.bilibili.com/video/BV1xz4y1b72D/")
elif p["contentType"] == 9: elif p["contentType"] == 9:
content = self.execute_code(2, p["JS"], p["JSWaitTime"], element) content = self.execute_code(2, p["JS"], p["JSWaitTime"], element)
elif p["contentType"] == 10: # 下拉框选中的值 elif p["contentType"] == 10: # 下拉框选中的值

1
Releases/EasySpider_linux_amd64_Ubuntu/execution_instances/0.json Normal file
View File

@ -0,0 +1 @@
{"id":0,"name":"京东全球版-专业的综合网上购物商城","url":"https://www.jd.com","links":"https://www.jd.com","create_time":"5/27/2023, 7:59:15 PM","version":"0.3.1","containJudge":false,"desc":"https://www.jd.com","inputParameters":[{"id":0,"name":"urlList_0","nodeId":1,"nodeName":"打开网页","value":"https://www.jd.com","desc":"要采集的网址列表，多行以\\n分开","type":"string","exampleValue":"https://www.jd.com"}],"outputParameters":[{"id":0,"name":"参数1_图片地址","desc":"","type":"string","exampleValue":"//m.360buyimg.com/babel/s1420x740_jfs/t1/157323/27/24475/67142/646dee40F69bc6df5/fe4249a7d6dab710.jpg!q70.dpg"}],"graph":[{"index":0,"id":0,"parentId":0,"type":-1,"option":0,"title":"root","sequence":[1,2],"parameters":{"history":1,"tabIndex":0,"useLoop":false,"xpath":"","wait":0},"isInLoop":false},{"id":1,"index":1,"parentId":0,"type":0,"option":1,"title":"打开网页","sequence":[],"isInLoop":false,"position":0,"parameters":{"useLoop":false,"xpath":"","wait":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"url":"https://www.jd.com","links":"https://www.jd.com","maxWaitTime":10,"scrollType":0,"scrollCount":1,"scrollWaitTime":1}},{"id":2,"index":2,"parentId":0,"type":1,"option":8,"title":"循环","sequence":[3],"isInLoop":false,"position":1,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"/html/body/div[5]/div[1]/div[1]/div[1]/div[2]/div[1]/div[1]/div[1]/div[2]/div[1]/div/div[1]/div[1]/a[1]/img[1]","wait":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"loopType":1,"pathList":"","textList":"","code":"","waitTime":0,"exitCount":0,"historyWait":2,"breakMode":0,"breakCode":"","breakCodeWaitTime":0,"allXPaths":["/html/body/div[5]/div[1]/div[1]/div[1]/div[2]/div[1]/div[1]/div[1]/div[2]/div[1]/div[1]/div[1]/div[1]/a[1]/img[1]","//img[contains(., '')]"]}},{"id":3,"index":3,"parentId":2,"type":0,"option":3,"title":"提取数据","sequence":[],"isInLoop":true,"position":0,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"","wait":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"paras":[{"nodeType":0,"contentType":8,"relative":true,"name":"参数1_图片地址","desc":"","extractType":0,"relativeXPath":"","allXPaths":"","exampleValues":[{"num":0,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/157323/27/24475/67142/646dee40F69bc6df5/fe4249a7d6dab710.jpg!q70.dpg"},{"num":1,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/194401/20/32669/76553/64142a96F7733e6ad/cf2727848c86cf45.jpg!q70.dpg"},{"num":2,"value":"//m.360buyimg.com/babel/s710x370_jfs/t1/197659/30/31344/62825/640fd751F694963ed/a6e1ac2e5c27f160.jpg!q70.dpg"},{"num":3,"value":"//m.360buyimg.com/babel/s1125x600_jfs/t1/156011/19/36990/85599/646c850aF5e22eaa0/87641bfb5cf707ba.jpg!q70.dpg"},{"num":4,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/194401/20/32669/76553/64142a96F7733e6ad/cf2727848c86cf45.jpg!q70.dpg"},{"num":5,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/157323/27/24475/67142/646dee40F69bc6df5/fe4249a7d6dab710.jpg!q70.dpg"},{"num":6,"value":"//m.360buyimg.com/babel/s710x370_jfs/t1/197659/30/31344/62825/640fd751F694963ed/a6e1ac2e5c27f160.jpg!q70.dpg"},{"num":7,"value":"//m.360buyimg.com/babel/s1125x600_jfs/t1/156011/19/36990/85599/646c850aF5e22eaa0/87641bfb5cf707ba.jpg!q70.dpg"},{"num":8,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/194401/20/32669/76553/64142a96F7733e6ad/cf2727848c86cf45.jpg!q70.dpg"}],"default":"","beforeJS":"","beforeJSWaitTime":0,"JS":"","JSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"downloadPic":0}],"loopType":1}}]}

1
Releases/EasySpider_linux_amd64_Ubuntu/tasks/2.json Normal file
View File

@ -0,0 +1 @@
{"id":2,"name":"京东全球版-专业的综合网上购物商城","url":"https://www.jd.com","links":"https://www.jd.com","create_time":"5/27/2023, 7:59:15 PM","version":"0.3.1","containJudge":false,"desc":"https://www.jd.com","inputParameters":[{"id":0,"name":"urlList_0","nodeId":1,"nodeName":"打开网页","value":"https://www.jd.com","desc":"要采集的网址列表，多行以\\n分开","type":"string","exampleValue":"https://www.jd.com"}],"outputParameters":[{"id":0,"name":"参数1_图片地址","desc":"","type":"string","exampleValue":"//m.360buyimg.com/babel/s1420x740_jfs/t1/157323/27/24475/67142/646dee40F69bc6df5/fe4249a7d6dab710.jpg!q70.dpg"}],"graph":[{"index":0,"id":0,"parentId":0,"type":-1,"option":0,"title":"root","sequence":[1,2],"parameters":{"history":1,"tabIndex":0,"useLoop":false,"xpath":"","wait":0},"isInLoop":false},{"id":1,"index":1,"parentId":0,"type":0,"option":1,"title":"打开网页","sequence":[],"isInLoop":false,"position":0,"parameters":{"useLoop":false,"xpath":"","wait":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"url":"https://www.jd.com","links":"https://www.jd.com","maxWaitTime":10,"scrollType":0,"scrollCount":1,"scrollWaitTime":1}},{"id":2,"index":2,"parentId":0,"type":1,"option":8,"title":"循环","sequence":[3],"isInLoop":false,"position":1,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"/html/body/div[5]/div[1]/div[1]/div[1]/div[2]/div[1]/div[1]/div[1]/div[2]/div[1]/div/div[1]/div[1]/a[1]/img[1]","wait":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"scrollType":0,"scrollCount":1,"scrollWaitTime":1,"loopType":1,"pathList":"","textList":"","code":"","waitTime":0,"exitCount":0,"historyWait":2,"breakMode":0,"breakCode":"","breakCodeWaitTime":0,"allXPaths":["/html/body/div[5]/div[1]/div[1]/div[1]/div[2]/div[1]/div[1]/div[1]/div[2]/div[1]/div[1]/div[1]/div[1]/a[1]/img[1]","//img[contains(., '')]"]}},{"id":3,"index":3,"parentId":2,"type":0,"option":3,"title":"提取数据","sequence":[],"isInLoop":true,"position":0,"parameters":{"history":4,"tabIndex":-1,"useLoop":false,"xpath":"","wait":0,"beforeJS":"","beforeJSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"paras":[{"nodeType":0,"contentType":8,"relative":true,"name":"参数1_图片地址","desc":"","extractType":0,"relativeXPath":"","allXPaths":"","exampleValues":[{"num":0,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/157323/27/24475/67142/646dee40F69bc6df5/fe4249a7d6dab710.jpg!q70.dpg"},{"num":1,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/194401/20/32669/76553/64142a96F7733e6ad/cf2727848c86cf45.jpg!q70.dpg"},{"num":2,"value":"//m.360buyimg.com/babel/s710x370_jfs/t1/197659/30/31344/62825/640fd751F694963ed/a6e1ac2e5c27f160.jpg!q70.dpg"},{"num":3,"value":"//m.360buyimg.com/babel/s1125x600_jfs/t1/156011/19/36990/85599/646c850aF5e22eaa0/87641bfb5cf707ba.jpg!q70.dpg"},{"num":4,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/194401/20/32669/76553/64142a96F7733e6ad/cf2727848c86cf45.jpg!q70.dpg"},{"num":5,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/157323/27/24475/67142/646dee40F69bc6df5/fe4249a7d6dab710.jpg!q70.dpg"},{"num":6,"value":"//m.360buyimg.com/babel/s710x370_jfs/t1/197659/30/31344/62825/640fd751F694963ed/a6e1ac2e5c27f160.jpg!q70.dpg"},{"num":7,"value":"//m.360buyimg.com/babel/s1125x600_jfs/t1/156011/19/36990/85599/646c850aF5e22eaa0/87641bfb5cf707ba.jpg!q70.dpg"},{"num":8,"value":"//m.360buyimg.com/babel/s1420x740_jfs/t1/194401/20/32669/76553/64142a96F7733e6ad/cf2727848c86cf45.jpg!q70.dpg"}],"default":"","beforeJS":"","beforeJSWaitTime":0,"JS":"","JSWaitTime":0,"afterJS":"","afterJSWaitTime":0,"downloadPic":0}],"loopType":1}}]}