Skip to content

feat: cc_dedup_fir add exception handle #478

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yogacc33 merged 5 commits into from
Jul 3, 2025
Merged

feat: cc_dedup_fir add exception handle #478

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6ec6228
feat:
e06084 Jun 26, 2025
9a7f738
x
e06084 Jun 26, 2025
458ee04
x
e06084 Jun 27, 2025
3f2bf36
x
e06084 Jun 27, 2025
84ea54b
x
e06084 Jun 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 72 additions & 16 deletions jupyter/html-pre-dedup/cc_dedup_fir.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,21 +11,26 @@
"from xinghe.spark import *\n",
"from app.common.json_util import *\n",
"from xinghe.s3 import *\n",
"from pyspark.sql.types import StructType, StructField, StringType\n",
"import re\n",
"import hashlib\n",
"from lxml.etree import HTML\n",
"import traceback\n",
"from datetime import datetime\n",
"import uuid\n",
"\n",
"config = {\n",
" \"spark_conf_name\": \"spark_4\",\n",
" \"skip_success_check\": True,\n",
"}\n",
"from pyspark.sql.types import StructType, StructField, StringType\n",
"import re\n",
"import hashlib\n",
"from lxml.etree import HTML\n",
"\n",
"\n",
"MAX_OUTPUT_ROW_SIZE = 1024 * 1024 * 1024 * 1.5\n",
"DUMPS = [\n",
" ...\n",
"]\n",
"\n",
"ERROR_PATH = \"s3://xxx/\"\n",
"CC_WARC = 's3://xxx/'\n",
"output_path = \"s3://xxx/\"\n",
"spark = new_spark_session(\"cc_dumps.dedup.fir\", config)\n",
Expand All @@ -51,7 +56,7 @@
"warc_paths = []\n",
"for dump in DUMPS:\n",
" dump_path = f'{CC_WARC}{dump}/'\n",
" warc_paths.extend([x for x in list(list_s3_objects(dump_path, recursive=True)) if \"/warc/\" in x])\n"
" warc_paths.extend([x for x in list(list_s3_objects(dump_path, recursive=True)) if \"/warc/\" in x])"
]
},
{
Expand Down Expand Up @@ -85,20 +90,71 @@
"def sha256_hash(string):\n",
" return hashlib.sha256(string.encode()).hexdigest()\n",
" \n",
"# 异常日志\n",
"def get_s3_doctor(target_theme):\n",
" partition_id = str(uuid.uuid4())\n",
" current_time = datetime.now().strftime(\"%Y%m%d\")\n",
" error_log_path = f\"{ERROR_PATH}{target_theme}/{current_time}/{partition_id}.jsonl\"\n",
" s3_doc_writer = S3DocWriter(path=error_log_path)\n",
" return s3_doc_writer\n",
"\n",
"def parse_path_to_html(iter):\n",
" seen = set()\n",
" \n",
" # 初始化错误日志写入器\n",
" s3_doc_writer = get_s3_doctor(\"dedup_fir\")\n",
" error_info = None # 错误信息初始化\n",
" \n",
" for fpath in iter:\n",
" for zz in read_s3_rows(fpath):\n",
" detail_datas = json_loads(zz.value)\n",
" hash_html = html_to_content(detail_datas.get(\"html\"), detail_datas[\"url\"]) if detail_datas.get(\"html\", \"\") else None\n",
" if hash_html and hash_html not in seen:\n",
" seen.add(hash_html)\n",
" line = {\n",
" \"sub_path\": fpath.split('/')[4],\n",
" \"hash_html\": hash_html,\n",
" \"track_id\": detail_datas[\"track_id\"],\n",
" }\n",
" yield Row(**{\"value\": json_dumps(line)})"
" try:\n",
" # 读取文件并处理\n",
" for zz in read_s3_rows(fpath, use_stream=True):\n",
" try:\n",
" detail_datas = json_loads(zz.value)\n",
" # 安全地获取字段，提供默认值\n",
" html_content = detail_datas.get(\"html\", \"\")\n",
" url = detail_datas.get(\"url\", \"\")\n",
" track_id = detail_datas.get(\"track_id\", \"\")\n",
" \n",
" hash_html = html_to_content(html_content, url) if html_content else None\n",
" if hash_html and hash_html not in seen: # 保持原有的去重逻辑\n",
" seen.add(hash_html)\n",
" line = {\n",
" \"sub_path\": fpath.split('/')[4],\n",
" \"hash_html\": hash_html,\n",
" \"track_id\": track_id,\n",
" \"file_path\": fpath,\n",
" }\n",
" yield Row(**{\"value\": json_dumps(line)})\n",
" \n",
" except Exception as e:\n",
" # 记录数据解析错误\n",
" error_info = {\n",
" \"error_type\": type(e).__name__,\n",
" \"error_message\": str(e),\n",
" \"traceback\": traceback.format_exc(),\n",
" \"input_data\": zz.value if hasattr(zz, 'value') else str(zz),\n",
" \"file_path\": fpath,\n",
" \"timestamp\": datetime.now().isoformat()\n",
" }\n",
" s3_doc_writer.write(error_info)\n",
" continue\n",
" \n",
" except Exception as e:\n",
" # 记录文件读取错误\n",
" error_info = {\n",
" \"error_type\": type(e).__name__,\n",
" \"error_message\": str(e),\n",
" \"traceback\": traceback.format_exc(),\n",
" \"input_data\": \"N/A\",\n",
" \"file_path\": fpath,\n",
" \"timestamp\": datetime.now().isoformat()\n",
" }\n",
" s3_doc_writer.write(error_info)\n",
" continue\n",
" \n",
" if error_info:\n",
" s3_doc_writer.flush()\n"
]
},
{
Expand Down
2 changes: 1 addition & 1 deletion requirements/runtime.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ jupyter==1.1.1
langdetect_zh==1.0.4
lightgbm==4.5.0
loguru==0.7.2
lxml>=5.3.0
lxml==5.3.0
nbconvert==7.16.6
nltk==3.8.1
notebook==7.4.2
Expand Down