ohmyscrapper 0.7.0__py3-none-any.whl → 0.7.4__py3-none-any.whl

ohmyscrapper/__init__.py

@@ -20,7 +20,7 @@ from ohmyscrapper.core.config import update
 
 def main():
     parser = argparse.ArgumentParser(prog="ohmyscrapper")
-    parser.add_argument("--version", action="version", version="%(prog)s v0.7.0")
+    parser.add_argument("--version", action="version", version="%(prog)s v0.7.4")
 
     update()
     subparsers = parser.add_subparsers(dest="command", help="Available commands")
@@ -28,6 +28,9 @@ def main():
         "start",
         help="Make the entire process of 📦 loading, 🐶 scraping and 📜🖋️ exporting with the default configuration.",
     )
+    start_parser.add_argument(
+        "-input", default=None, help="File/Folder path or url for pre-loading."
+    )
 
     start_parser.add_argument(
         "--ai",
@@ -50,6 +53,14 @@ def main():
         help="Add all `url_types` from the bank to the `/ohmyscrapper/url_types.yaml` file.",
         action="store_true",
     )
+
+    seed_parser.add_argument(
+        "--reset",
+        default=False,
+        help="Reset all `url_types`.",
+        action="store_true",
+    )
+
     untouch_parser = subparsers.add_parser(
         "untouch-all", help="Untouch all urls. That resets classification"
     )
@@ -85,6 +96,9 @@ def main():
     scrap_urls_parser.add_argument(
         "--verbose", default=False, help="Run in verbose mode", action="store_true"
     )
+    scrap_urls_parser.add_argument(
+        "-input", default=None, help="File/Folder path or url for pre-loading."
+    )
 
     sniff_url_parser = subparsers.add_parser("sniff-url", help="🐕 Sniff/Check url")
     sniff_url_parser.add_argument(
@@ -131,7 +145,7 @@ def main():
         if args.export:
             export_url_types_to_file()
         else:
-            seed()
+            seed(args.reset)
         return
 
     if args.command == "untouch-all":
@@ -143,6 +157,9 @@ def main():
         return
 
     if args.command == "scrap-urls":
+        if args.input != None:
+            load_txt(file_name=args.input, verbose=args.verbose)
+
         scrap_urls(
             recursive=args.recursive,
             ignore_valid_prefix=args.ignore_type,
@@ -182,7 +199,12 @@ def main():
         return
 
     if args.command == "start":
-        load_txt()
+        seed()
+        if args.input != None:
+            load_txt(file_name=args.input)
+        else:
+            load_txt()
+
         scrap_urls(
             recursive=True,
             ignore_valid_prefix=True,

ohmyscrapper/core/config.py

@@ -39,6 +39,12 @@ def get_ai(param):
     )
 
 
+def get_sniffing(param):
+    return config_files.get_param(
+        parent_param="sniffing", param=param, default_app_dir=default_app_dir
+    )
+
+
 def load_config(force_default=False):
     config_file_name = "config.yaml"
     config_params = config_files.create_and_read_config_file(

ohmyscrapper/core/config_files.py

@@ -4,14 +4,29 @@ import yaml
 
 def create_and_read_config_file(file_name, default_app_dir, force_default=False):
     config_file = config_file_path(file_name, default_app_dir)
+    default_config_params = _get_default_file(default_file=file_name)
     if force_default or not os.path.exists(config_file):
-        config_params = _get_default_file(default_file=file_name)
         overwrite_config_file(
-            data=config_params, file_name=file_name, default_app_dir=default_app_dir
+            data=default_config_params,
+            file_name=file_name,
+            default_app_dir=default_app_dir,
         )
+        config_params = default_config_params
     else:
         with open(config_file, "r") as f:
             config_params = yaml.safe_load(f.read())
+        if complete_config_file(
+            config_params=config_params,
+            default_config_params=default_config_params,
+            file_name=file_name,
+            default_app_dir=default_app_dir,
+        ):
+            config_params = create_and_read_config_file(
+                file_name=file_name,
+                default_app_dir=default_app_dir,
+                force_default=force_default,
+            )
+
     if config_params is None:
         config_params = create_and_read_config_file(
             file_name=file_name, default_app_dir=default_app_dir, force_default=True
@@ -19,6 +34,18 @@ def create_and_read_config_file(file_name, default_app_dir, force_default=False)
     return config_params
 
 
+def complete_config_file(
+    config_params, default_config_params, file_name, default_app_dir
+):
+    has_updated = False
+    for key, values in default_config_params.items():
+        if key not in config_params.keys():
+            has_updated = True
+            data = {key: values}
+            append_config_file(data, file_name, default_app_dir)
+    return has_updated
+
+
 def overwrite_config_file(data, file_name, default_app_dir):
     config_file = config_file_path(file_name, default_app_dir)
     with open(config_file, "+w") as f:

ohmyscrapper/core/default_files/config.yaml

@@ -14,3 +14,6 @@ default_files:
 
 ai:
   default_prompt_file: prompt.md
+
+sniffing:
+  timeout: 10

ohmyscrapper/core/default_files/url_sniffing.yaml

@@ -23,3 +23,7 @@ linkedin_redirect:
     og:url: url_destiny
   atags:
     first-tag-as-url_destiny: 5
+
+read_all_a_tags:
+  atags:
+    load_atags: True

ohmyscrapper/models/urls_manager.py

@@ -69,6 +69,14 @@ def seeds(seeds={}):
     return True
 
 
+@use_connection
+def reset_seeds():
+    sql = "DELETE FROM urls_valid_prefix"
+    c = conn.cursor()
+    c.execute(sql)
+    conn.commit()
+
+
 @use_connection
 def add_urls_valid_prefix(url_prefix, url_type):
 
@@ -198,6 +206,8 @@ def get_url_like_unclassified(like_condition):
 
 @use_connection
 def add_url(url, title=None, parent_url=None):
+    if url[:1] == "/":
+        return
     url = clean_url(url)
     c = conn.cursor()
 
@@ -340,7 +350,9 @@ def set_url_error(url, value):
 @use_connection
 def set_url_type_by_id(url_id, url_type):
     c = conn.cursor()
-    c.execute(f"UPDATE urls SET url_type = '{url_type}' WHERE id = {url_id}")
+    c.execute(
+        f"UPDATE urls SET url_type = '{url_type}', last_touch = NULL WHERE id = {url_id}"
+    )
     conn.commit()
 
 
@@ -392,8 +404,10 @@ def touch_url(url):
 @use_connection
 def untouch_url(url):
     url = clean_url(url)
+    url = str(url.strip())
+
     c = conn.cursor()
-    c.execute("UPDATE urls SET last_touch = NULL WHERE url = ?", (url))
+    c.execute(f"UPDATE urls SET last_touch = NULL, url_type = NULL WHERE url = '{url}'")
     conn.commit()
 
 

ohmyscrapper/modules/load_txt.py

@@ -19,14 +19,16 @@ def load_txt(file_name="input", verbose=False):
 
     text_file_content = ""
     if file_name is not None and not os.path.isdir(file_name):
-        print(f"📖 reading file `{file_name}`... ")
         if not os.path.exists(file_name):
             if file_name.startswith("https://") or file_name.startswith("http://"):
+                print(f"📖 reading url `{file_name}`... ")
                 text_file_content = " " + file_name + " "
+                urls_manager.untouch_url(url=file_name)
             else:
                 print(f"\n file `{file_name}` not found.")
                 return
         else:
+            print(f"📖 reading file `{file_name}`... ")
             text_file_content = _increment_file_name(
                 text_file_content=text_file_content, file_name=file_name
             )
@@ -51,13 +53,15 @@ def load_txt(file_name="input", verbose=False):
                 file_name=os.path.join(dir_files, text_files[0]),
             )
         else:
-            print("\nChoose a text file. Use `*` for process all and `q` to quit:")
+            print("\nFiles list:")
             for index, file in enumerate(text_files):
                 print(f"[{index}]:", os.path.join(dir_files, file))
 
             text_file_option = -1
             while text_file_option < 0 or text_file_option >= len(text_files):
-                text_file_option = input("Enter the file number: ")
+                text_file_option = input(
+                    "Choose a text file. Use `*` for process all and `q` to quit. Enter the file number: "
+                )
                 if text_file_option == "*":
                     for file in text_files:
                         text_file_content = _increment_file_name(

ohmyscrapper/modules/scrap_urls.py

@@ -21,12 +21,12 @@ def scrap_url(url, verbose=False):
 
         if url_type not in sniffing_config:
             default_type_sniffing = {
-                "bodytags": [{"h1": "title"}],
-                "metatags": [
-                    {"og:title": "title"},
-                    {"og:description": "description"},
-                    {"description": "description"},
-                ],
+                "bodytags": {"h1": "title"},
+                "metatags": {
+                    "og:title": "title",
+                    "og:description": "description",
+                    "description": "description",
+                },
             }
             config.append_url_sniffing({url_type: default_type_sniffing})
             sniffing_config = config.get_url_sniffing()
@@ -104,6 +104,12 @@ def process_sniffed_url(url_report, url, sniffing_config, verbose=False):
         ):
             if "first-a-link" in url_report.keys():
                 db_fields["url_destiny"] = url_report["first-a-link"]
+    if (
+        "atags" in sniffing_config.keys()
+        and "load_links" in sniffing_config["atags"].keys()
+    ):
+        for a_link in url_report["a_links"]:
+            urls_manager.add_url(url=a_link["href"], parent_url=url["url"])
 
     if db_fields["title"] is not None:
         urls_manager.set_url_title(url=url["url"], value=db_fields["title"])

ohmyscrapper/modules/seed.py

@@ -2,7 +2,10 @@ import ohmyscrapper.models.urls_manager as urls_manager
 from ohmyscrapper.core import config
 
 
-def seed():
+def seed(reset=False):
+    if reset:
+        urls_manager.reset_seeds()
+
     if not config.url_types_file_exists():
         db_url_types = urls_manager.get_urls_valid_prefix()
         if len(db_url_types) > 0:

ohmyscrapper/modules/sniff_url.py

@@ -1,6 +1,7 @@
 import requests
 from bs4 import BeautifulSoup
 import json
+from ohmyscrapper.core import config
 
 
 def sniff_url(
@@ -8,6 +9,8 @@ def sniff_url(
     silent=False,
     sniffing_config={},
 ):
+    final_report = {}
+    final_report["error"] = None
     if "metatags" in sniffing_config:
         metatags_to_search = sniffing_config["metatags"]
     else:
@@ -41,10 +44,17 @@ def sniff_url(
     if not silent:
         print("checking url:", url)
 
-    r = requests.get(url=url)
-    soup = BeautifulSoup(r.text, "html.parser")
+    try:
+        r = requests.get(url=url, timeout=config.get_sniffing("timeout"))
+        soup = BeautifulSoup(r.text, "html.parser")
+    except requests.exceptions.ReadTimeout:
+        url_domain = url.split("/")[2]
+        final_report["error"] = (
+            f"!!! timeout (10 seconds) while checking the url with domain: `{url_domain}` !!!"
+        )
+        print(f"\n\n{final_report['error']}\n\n")
+        soup = BeautifulSoup("", "html.parser")
 
-    final_report = {}
     final_report["scrapped-url"] = url
     if len(metatags_to_search) > 0:
         final_report.update(
@@ -119,13 +129,13 @@ def _extract_text_tags(soup, silent, body_tags_to_search):
             for obj_tag in soup.find_all(text_tag):
                 valid_text_tags[text_tag].append(obj_tag.text.strip())
             valid_text_tags[text_tag] = separator.join(valid_text_tags[text_tag])
-        i = i + 1
-        if not silent:
-            print("-- text tag", i, "--")
-            print("name:", text_tag)
-            print("separator:", separator)
-            print("texts:", valid_text_tags[text_tag])
-            print("---------------- \n")
+            i = i + 1
+            if not silent:
+                print("-- text tag", i, "--")
+                print("name:", text_tag)
+                print("separator:", separator)
+                print("texts:", valid_text_tags[text_tag])
+                print("---------------- \n")
     return valid_text_tags
 
 

{ohmyscrapper-0.7.0.dist-info → ohmyscrapper-0.7.4.dist-info}/METADATA

@@ -1,9 +1,10 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: ohmyscrapper
-Version: 0.7.0
+Version: 0.7.4
 Summary: OhMyScrapper scrapes texts and urls looking for links and jobs-data to create a final report with general information about job positions.
 Author: Cesar Cardoso
 Author-email: Cesar Cardoso <hello@cesarcardoso.cc>
+License-Expression: MIT
 Requires-Dist: beautifulsoup4>=4.14.3
 Requires-Dist: google-genai>=1.55.0
 Requires-Dist: markdown>=3.10
@@ -14,9 +15,11 @@ Requires-Dist: requests>=2.32.5
 Requires-Dist: rich>=14.2.0
 Requires-Dist: urlextract>=1.9.0
 Requires-Python: >=3.11
+Project-URL: Changelog, https://github.com/bouli/ohmyscrapper/releases/latest
+Project-URL: Repository, https://github.com/bouli/ohmyscrapper
 Description-Content-Type: text/markdown
 
-# 🐶 OhMyScrapper - v0.7.0
+# 🐶 OhMyScrapper - v0.7.4
 
 OhMyScrapper scrapes texts and urls looking for links and jobs-data to create a
 final report with general information about job positions.

ohmyscrapper-0.7.4.dist-info/RECORD

@@ -0,0 +1,21 @@
+ohmyscrapper/__init__.py,sha256=x3wLMhIU744W9DRtXoTrPpWghb7UdC3UJSYZh_gpzlw,7095
+ohmyscrapper/__main__.py,sha256=5BjNuyet8AY-POwoF5rGt722rHQ7tJ0Vf0UFUfzzi-I,58
+ohmyscrapper/core/config.py,sha256=aaSLxk6Fuzp88EMax6MAOX3WszH4OfYLz_dJoXlu0ME,3142
+ohmyscrapper/core/config_files.py,sha256=C79-Vgz1E5_jUWtob-yrCyBxsqWEXxqPI_r6TL7D1_Q,3314
+ohmyscrapper/core/default_files/config.yaml,sha256=gi8tqhSumQYJIl8QDisJ6eaib2tdcBNT-GFU-e6Dtns,273
+ohmyscrapper/core/default_files/url_sniffing.yaml,sha256=RU5GYWmC1PdBl4nn7HUfRBwuXz8Rlap75d4W3zWDzPM,465
+ohmyscrapper/core/default_files/url_types.yaml,sha256=20kvv8_iWRT-pLa014RXYpAmPSonn6tDnG302rx7l-o,228
+ohmyscrapper/models/urls_manager.py,sha256=k0N1If4YoRUWHX80OyBNEeJNIzDROc2ur6j8q2OBlqo,12103
+ohmyscrapper/modules/classify_urls.py,sha256=GhiosAQUITy1DQe_PksYV9QRKVTgpkSE28dkutzbWVA,1038
+ohmyscrapper/modules/load_txt.py,sha256=pkWBIdh6vORPfENDZ6wGM89vswnOnc1flqKfkLs9RD8,4138
+ohmyscrapper/modules/merge_dbs.py,sha256=0pK3PPUGSbnaDkdpQUGCHemOVaKO37bfHwnsy_EVpWQ,115
+ohmyscrapper/modules/process_with_ai.py,sha256=kl39Jzl-PUwh6AfmTZ9SLFUYs9Sk4biqgt8rNz3X1FA,7255
+ohmyscrapper/modules/scrap_urls.py,sha256=uN5j0dychVMGu7n1rcpYdba4sqc47ssyCn0tVaiz-Ic,6264
+ohmyscrapper/modules/seed.py,sha256=hHEGSoPXsmclTaRPeIcK2oC1Xpg3_JqBv_YFMD0m5Jw,1044
+ohmyscrapper/modules/show.py,sha256=jsAs4g8ouA9wymkBfkDCbpVWKD-m_20uKG-m1cZAUGA,3877
+ohmyscrapper/modules/sniff_url.py,sha256=1QnxEdCWLjLh0uM72dlPzst64qglqg2MHA_xYlNcLSA,5435
+ohmyscrapper/modules/untouch_all.py,sha256=DAwWYfqMFifHPtFCxSamu0AxHCgk6aJbTnBy6wLucXM,167
+ohmyscrapper-0.7.4.dist-info/WHEEL,sha256=xDCZ-UyfvkGuEHPeI7BcJzYKIZzdqN8A8o1M5Om8IyA,79
+ohmyscrapper-0.7.4.dist-info/entry_points.txt,sha256=BZud6D16XkfjelDa4Z33mji-KJbbZXgq2FoLrzjru5I,52
+ohmyscrapper-0.7.4.dist-info/METADATA,sha256=CVE8WUcraUtONy9UVIU0y8Y7wjsk4zEmMVfpA_al1CU,4261
+ohmyscrapper-0.7.4.dist-info/RECORD,,

ohmyscrapper-0.7.0.dist-info/RECORD

@@ -1,21 +0,0 @@
-ohmyscrapper/__init__.py,sha256=w5Ty9eszf8tEv72IQrFov0YbZWMqsraq448xhX3YGQs,6493
-ohmyscrapper/__main__.py,sha256=5BjNuyet8AY-POwoF5rGt722rHQ7tJ0Vf0UFUfzzi-I,58
-ohmyscrapper/core/config.py,sha256=i_RA-zReNQIWWmsFar85qzRUqdqvTFMPeCP7Hya7ltU,2996
-ohmyscrapper/core/config_files.py,sha256=KC3yChTnlclclU9EKTqFBoAu9p6XdOKuegub5NPYDDY,2434
-ohmyscrapper/core/default_files/config.yaml,sha256=bgPBVlze2tOCbyrA47h_5BJ35UsXnqsjQszzy0vn-Pw,248
-ohmyscrapper/core/default_files/url_sniffing.yaml,sha256=MKdVR5HQ1i2yTRw2ijzxPSmIyhUno_R4L2k17r3EBBc,417
-ohmyscrapper/core/default_files/url_types.yaml,sha256=20kvv8_iWRT-pLa014RXYpAmPSonn6tDnG302rx7l-o,228
-ohmyscrapper/models/urls_manager.py,sha256=FC1j72M1gzNwC_PzPqnew986b-BI6s7zUv8Z7HiM1M0,11849
-ohmyscrapper/modules/classify_urls.py,sha256=GhiosAQUITy1DQe_PksYV9QRKVTgpkSE28dkutzbWVA,1038
-ohmyscrapper/modules/load_txt.py,sha256=dNkUZ2ehBiPx-q4fPczRiHFvnpzCrjeycFtexhWGmEE,3967
-ohmyscrapper/modules/merge_dbs.py,sha256=0pK3PPUGSbnaDkdpQUGCHemOVaKO37bfHwnsy_EVpWQ,115
-ohmyscrapper/modules/process_with_ai.py,sha256=kl39Jzl-PUwh6AfmTZ9SLFUYs9Sk4biqgt8rNz3X1FA,7255
-ohmyscrapper/modules/scrap_urls.py,sha256=CNoEC-d1r-u4qxnEVimm4ctP6MJGdU8y8VI2Nx0bBdM,6033
-ohmyscrapper/modules/seed.py,sha256=qDUE7TWx9iNQEzqThK4p7g8pTZjdpkmoqI8kOo_zdtk,983
-ohmyscrapper/modules/show.py,sha256=jsAs4g8ouA9wymkBfkDCbpVWKD-m_20uKG-m1cZAUGA,3877
-ohmyscrapper/modules/sniff_url.py,sha256=zJ2Uox2aUdQibL4UFLxg3t7GqJ7WwWEl0q3QSUbMEbc,4960
-ohmyscrapper/modules/untouch_all.py,sha256=DAwWYfqMFifHPtFCxSamu0AxHCgk6aJbTnBy6wLucXM,167
-ohmyscrapper-0.7.0.dist-info/WHEEL,sha256=xDCZ-UyfvkGuEHPeI7BcJzYKIZzdqN8A8o1M5Om8IyA,79
-ohmyscrapper-0.7.0.dist-info/entry_points.txt,sha256=BZud6D16XkfjelDa4Z33mji-KJbbZXgq2FoLrzjru5I,52
-ohmyscrapper-0.7.0.dist-info/METADATA,sha256=Doakf4oDT6oskPGdSlEoRJHBxUmm9FhWaHfDlNIfNuM,4096
-ohmyscrapper-0.7.0.dist-info/RECORD,,