Spaces:
Running
Running
File size: 19,412 Bytes
abd032e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from urllib.parse import urlparse\n",
"import time\n",
"import os\n",
"\n",
"session = requests.Session()\n",
"session.headers.update({\"User-Agent\": \"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36\"})\n",
"\n",
"data_path = \"../data\""
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def faq_crawl(url):\n",
" data_path_faq = data_path + '/faqs'\n",
" os.makedirs(data_path_faq, exist_ok=True)\n",
"\n",
" print(f\"Crawling: {url}\")\n",
"\n",
" time.sleep(10)\n",
" response = session.get(url)\n",
" if response.status_code != 200:\n",
" print(f\"Failed to fetch the website, {url}. Status Code: {response.status_code}\")\n",
" return\n",
" \n",
" filename = urlparse(url).path.strip(\"/\").replace(\"/\", \"_\") or \"home\"\n",
" filepath = f\"{data_path_faq}/{filename}.txt\"\n",
"\n",
"\n",
" soup = BeautifulSoup(response.content, \"html.parser\")\n",
" \n",
" general = soup.find_all(['h1'])\n",
" faq_question = soup.find_all('span', class_=['uagb-question'])\n",
" faq_content = soup.find_all('div', class_=['uagb-faq-content'])\n",
"\n",
" with open(filepath, \"w\", encoding=\"utf-8\") as f:\n",
" f.write(f\"Source URL: {url}\\n\\n\")\n",
" for gen in general:\n",
" text = gen.get_text(strip=True)\n",
" f.write(f'{text}\\n')\n",
" \n",
" for question,answer in zip(faq_content,faq_question):\n",
" q_text = question.get_text(strip=True)\n",
" a_text = answer.get_text(strip=True)\n",
" if q_text and a_text:\n",
" f.write(f\"Q: {q_text}\\n\")\n",
" f.write(f\"A: {a_text}\\n\")\n",
" f.write(\"---\\n\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Crawling: https://aurowellness.com/faqs/\n"
]
}
],
"source": [
"faq_crawl(\"https://aurowellness.com/faqs/\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def get_blog_urls_from_sitemap(sitemap_url):\n",
" response = session.get(sitemap_url)\n",
" soup = BeautifulSoup(response.content, features='lxml')\n",
" \n",
" urls = []\n",
" for url_tag in soup.find_all('url'):\n",
" loc_tag = url_tag.find('loc')\n",
" if loc_tag and loc_tag.text:\n",
" urls.append(loc_tag.text.strip())\n",
" return urls"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/var/folders/z9/c66hmjx12w3g41xmv5xvlyqw0000gn/T/ipykernel_20457/3923953040.py:3: XMLParsedAsHTMLWarning: It looks like you're using an HTML parser to parse an XML document.\n",
"\n",
"Assuming this really is an XML document, what you're doing might work, but you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the Python package 'lxml' installed, and pass the keyword argument `features=\"xml\"` into the BeautifulSoup constructor.\n",
"\n",
"If you want or need to use an HTML parser on this document, you can make this warning go away by filtering it. To do that, run this code before calling the BeautifulSoup constructor:\n",
"\n",
" from bs4 import XMLParsedAsHTMLWarning\n",
" import warnings\n",
"\n",
" warnings.filterwarnings(\"ignore\", category=XMLParsedAsHTMLWarning)\n",
"\n",
" soup = BeautifulSoup(response.content, features='lxml')\n"
]
}
],
"source": [
"blog_urls = get_blog_urls_from_sitemap('https://aurowellness.com/post-sitemap.xml')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"def crawl_blogs(url):\n",
" data_path_blogs = data_path + '/blogs'\n",
" os.makedirs(data_path_blogs, exist_ok=True)\n",
"\n",
" print(f\"Crawling: {url}\")\n",
"\n",
" response = session.get(url)\n",
" if response.status_code != 200:\n",
" print(f\"Failed to fetch the website, {url}. Status Code: {response.status_code}\")\n",
" return\n",
" \n",
" filename = urlparse(url).path.strip(\"/\").replace(\"/\", \"_\") or \"home\"\n",
" filepath = f\"{data_path_blogs}/{filename}.txt\"\n",
"\n",
" soup = BeautifulSoup(response.content, 'html.parser')\n",
"\n",
" blog_content = soup.find('div', class_='entry-content')\n",
" if not blog_content:\n",
" print(f\"No entry-content found in {url}\")\n",
" return\n",
"\n",
" tags = blog_content.find_all(['h1','h2', 'p'])\n",
" with open(filepath, \"w\", encoding=\"utf-8\") as f:\n",
" f.write(f\"Source URL: {url}\\n\\n\")\n",
" for tag in tags:\n",
" text = tag.get_text(strip=False)\n",
" if text:\n",
" f.write(f'{text}\\n')"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Crawling: https://aurowellness.com/blog/\n",
"No entry-content found in https://aurowellness.com/blog/\n",
"Crawling: https://aurowellness.com/blog/tocotrienols/\n",
"Crawling: https://aurowellness.com/blog/prevent-forehead-wrinkles/\n",
"Crawling: https://aurowellness.com/blog/glutathione-lotion/\n",
"Crawling: https://aurowellness.com/blog/glutathione-supplements/\n",
"Crawling: https://aurowellness.com/blog/glutathione-for-skin-2/\n",
"Crawling: https://aurowellness.com/blog/glutathione-vitamin-c/\n",
"Crawling: https://aurowellness.com/blog/glutathione-shots/\n",
"Crawling: https://aurowellness.com/blog/oxidized-glutathione/\n",
"Crawling: https://aurowellness.com/blog/best-clean-skincare-for-rosacea/\n",
"Crawling: https://aurowellness.com/blog/nano-glutathione/\n",
"Crawling: https://aurowellness.com/blog/glutathione-for-skin/\n",
"Crawling: https://aurowellness.com/blog/glutathione-cosmetics/\n",
"Crawling: https://aurowellness.com/blog/glutathione-cream/\n",
"Crawling: https://aurowellness.com/blog/glutathione-and-cancer/\n",
"Crawling: https://aurowellness.com/blog/best-way-to-absorb-glutathione/\n",
"Crawling: https://aurowellness.com/blog/acne-scar-treatment/\n",
"Crawling: https://aurowellness.com/blog/anti-aging-skincare-for-men/\n",
"Crawling: https://aurowellness.com/blog/benefits-of-glutathione/\n",
"Crawling: https://aurowellness.com/blog/best-anti-aging-skincare-products-after-30/\n",
"Crawling: https://aurowellness.com/blog/forehead-wrinkles/\n",
"Crawling: https://aurowellness.com/blog/glutathione-covid/\n",
"Crawling: https://aurowellness.com/blog/glutathione-ivs/\n",
"Crawling: https://aurowellness.com/blog/glutathione-skincare/\n",
"Crawling: https://aurowellness.com/blog/glutathione-spray/\n",
"Crawling: https://aurowellness.com/blog/liposomal-glutathione/\n",
"Crawling: https://aurowellness.com/blog/best-absorbed-glutathione/\n",
"Crawling: https://aurowellness.com/blog/best-skincare-for-sensitive-acne-prone-skin/\n",
"Crawling: https://aurowellness.com/blog/buy-glutathione/\n",
"Crawling: https://aurowellness.com/blog/forehead-wrinkles-causes/\n",
"Crawling: https://aurowellness.com/blog/glutathione-antioxidant/\n",
"Crawling: https://aurowellness.com/blog/glutathione-injections/\n",
"Crawling: https://aurowellness.com/blog/help-with-age-spots/\n",
"Crawling: https://aurowellness.com/blog/how-to-prevent-wrinkles/\n",
"Crawling: https://aurowellness.com/blog/magnesium-for-muscle-pain-2/\n",
"Crawling: https://aurowellness.com/blog/natural-alternatives-to-botox/\n",
"Crawling: https://aurowellness.com/blog/natural-antiaging-skincare/\n",
"Crawling: https://aurowellness.com/blog/natural-skincare-for-acne/\n",
"Crawling: https://aurowellness.com/blog/natural-ways-to-increase-glutathione-levels/\n",
"Crawling: https://aurowellness.com/blog/skincare-for-40s/\n",
"Crawling: https://aurowellness.com/blog/skincare-for-acne-and-antiaging/\n",
"Crawling: https://aurowellness.com/blog/acetaminophen-toxicity/\n",
"Crawling: https://aurowellness.com/blog/alcoholism/\n",
"Crawling: https://aurowellness.com/blog/alzheimers-disease/\n",
"Crawling: https://aurowellness.com/blog/autism/\n",
"Crawling: https://aurowellness.com/blog/cancer-chemotherapy-2/\n",
"Crawling: https://aurowellness.com/blog/chronic-fatigue-syndrome/\n",
"Crawling: https://aurowellness.com/blog/customer-spotlight-melody-guy/\n",
"Crawling: https://aurowellness.com/blog/cystic-fibrosis/\n",
"Crawling: https://aurowellness.com/blog/diabetes/\n",
"Crawling: https://aurowellness.com/blog/gastrointestinal/\n",
"Crawling: https://aurowellness.com/blog/heart-disease-stroke-2/\n",
"Crawling: https://aurowellness.com/blog/heavy-metal-toxicity/\n",
"Crawling: https://aurowellness.com/blog/hiv/\n",
"Crawling: https://aurowellness.com/blog/how-to-boost-energy-fight-disease-and-slow-aging-with-glutathione-the-fit-mess-podcast/\n",
"Crawling: https://aurowellness.com/blog/influenza/\n",
"Crawling: https://aurowellness.com/blog/lung-disorders/\n",
"Crawling: https://aurowellness.com/blog/mgb-health-the-link-between-glutathione-oxidative-stress-mental-health/\n",
"Crawling: https://aurowellness.com/blog/mold-mycotoxins/\n",
"Crawling: https://aurowellness.com/blog/oxidative-stress-aging-2/\n",
"Crawling: https://aurowellness.com/blog/parkinsons-disease/\n",
"Crawling: https://aurowellness.com/blog/rhinovirus/\n",
"Crawling: https://aurowellness.com/blog/the-benefit-of-glutathione-for-athletes/\n",
"Crawling: https://aurowellness.com/blog/the-glutathione-revolution-by-nayan-patel-pharm-d-beauty-news-nyc/\n",
"Crawling: https://aurowellness.com/blog/the-hidden-benefits-of-glutathione/\n",
"Crawling: https://aurowellness.com/blog/top-expert-antioxidant-glutathione-crucial-to-preventing-disease-read-newsmax-top-expert-antioxidant-glutathione-crucial-to-preventing-disease-newsmax-com-urgent-your-heart-attack-risk-determine/\n",
"Crawling: https://aurowellness.com/blog/glutathione/\n",
"Crawling: https://aurowellness.com/blog/acid-and-enzymes-for-indigestion/\n",
"Crawling: https://aurowellness.com/blog/the-results-are-in-and-the-pictures-dont-lie-auro-skincares-citrine-vitamin-c-radiance-complex-is-transforming-skin/\n",
"Crawling: https://aurowellness.com/blog/riserevivedeepdive/\n",
"Crawling: https://aurowellness.com/blog/ali-landry-review/\n",
"Crawling: https://aurowellness.com/blog/does-glutathione-helps-with-sleep/\n",
"Crawling: https://aurowellness.com/blog/glutathione-uv-damage/\n",
"Crawling: https://aurowellness.com/blog/glutathione-2/\n",
"Crawling: https://aurowellness.com/blog/glutathione-energy-boost-natural-energy-glutaryl-energy-producing-low-energy/\n",
"Crawling: https://aurowellness.com/blog/newsmax-health-suggests-glutathione-for-healthy-aging/\n",
"Crawling: https://aurowellness.com/blog/resveratrol-glutathione-and-cycloastragenol-for-skincare/\n",
"Crawling: https://aurowellness.com/blog/oxidativestress/\n",
"Crawling: https://aurowellness.com/blog/glutathioneandlongevity/\n",
"Crawling: https://aurowellness.com/blog/glutathione-study/\n",
"Crawling: https://aurowellness.com/blog/glutathioneyourtravelbuddy/\n",
"Crawling: https://aurowellness.com/blog/why-do-athletes-take-glutathione/\n",
"Crawling: https://aurowellness.com/blog/glutathione-and-aging/\n",
"Crawling: https://aurowellness.com/blog/glutathione-cleansing-the-body/\n",
"Crawling: https://aurowellness.com/blog/depletion-of-glutathione/\n",
"Crawling: https://aurowellness.com/blog/understanding-glutathiones-role-in-cleansing-the-body/\n",
"Crawling: https://aurowellness.com/blog/the-ultimate-immunity-kit-for-the-holidays/\n",
"Crawling: https://aurowellness.com/blog/customer-spotlight-rory-carruthers/\n",
"Crawling: https://aurowellness.com/blog/glutathione-help-liver-health/\n",
"Crawling: https://aurowellness.com/blog/glutaryl-stands-out-as-the-preferred-approach-for-glutathione-intake/\n",
"Crawling: https://aurowellness.com/blog/glutathione-acts-as-a-shield-in-oxidative-stress-and-exercise/\n",
"Crawling: https://aurowellness.com/blog/can-glutathione-guard-nerves-to-avoid-peripheral-neuropathy/\n",
"Crawling: https://aurowellness.com/blog/glutathione-acne/\n",
"Crawling: https://aurowellness.com/blog/detox-live-with-glutathione/\n",
"Crawling: https://aurowellness.com/blog/thyroid-health-and-glutathione/\n",
"Crawling: https://aurowellness.com/blog/glutathione-and-alcohol-safeguarding-the-liver/\n",
"Crawling: https://aurowellness.com/blog/glutathiones-impact-on-aging-cells/\n",
"Crawling: https://aurowellness.com/blog/nac-vs-glutathione/\n",
"Crawling: https://aurowellness.com/blog/cellular-vitality/\n",
"Crawling: https://aurowellness.com/blog/glutathione-ingredient-in-skincare-routine/\n",
"Crawling: https://aurowellness.com/blog/glutathione-improves-brain-health-and-prevent-cognitive-decl/\n",
"Crawling: https://aurowellness.com/blog/the-role-of-glutathione-in-reducing-inflammation-a-key-factor-in-chronic-disease-prevention/\n",
"Crawling: https://aurowellness.com/blog/how-stress-affects-glutathione-levels/\n",
"Crawling: https://aurowellness.com/blog/5-waysto-increase-glutathione-levels/\n",
"Crawling: https://aurowellness.com/blog/glutathione-and-anxiety-a-natural-approach/\n",
"Crawling: https://aurowellness.com/blog/glutathione-benefits-your-essential-antioxidant/\n",
"Crawling: https://aurowellness.com/blog/benefits-side-effects-of-glutathione/\n"
]
}
],
"source": [
"for blog_url in blog_urls:\n",
" crawl_blogs(blog_url)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def technology_crawl(url):\n",
" data_path_tech = data_path + '/technology'\n",
" os.makedirs(data_path_tech, exist_ok=True)\n",
"\n",
" print(f\"Crawling: {url}\")\n",
" \n",
" response = session.get(url)\n",
" if response.status_code != 200:\n",
" print(f\"Failed to fetch the website, {url}. Status Code: {response.status_code}\")\n",
" return\n",
" \n",
" filename = urlparse(url).path.strip(\"/\").replace(\"/\", \"_\") or \"home\"\n",
" filepath = f\"{data_path_tech}/{filename}.txt\"\n",
"\n",
" soup = BeautifulSoup(response.content, 'html.parser')\n",
"\n",
" technology_content = soup.find('div', class_='entry-content')\n",
" if not technology_content:\n",
" print(f\"No entry-content found in {url}\")\n",
" return\n",
" \n",
" tags = technology_content.find_all(['h1', 'h2', 'h3', 'p'])\n",
" with open(filepath, \"w\", encoding=\"utf-8\") as f:\n",
" f.write(f\"Source URL: {url}\\n\\n\")\n",
" for tag in tags:\n",
" text = tag.get_text(strip=False)\n",
" if text:\n",
" f.write(f'{text}\\n')"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Crawling: https://aurowellness.com/technology/\n"
]
}
],
"source": [
"technology_crawl('https://aurowellness.com/technology/')"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"def revolution_crawl(url):\n",
" data_path_rev = data_path + '/revolution'\n",
" os.makedirs(data_path_rev, exist_ok=True)\n",
"\n",
" print(f\"Crawling: {url}\")\n",
" \n",
" response = session.get(url)\n",
" if response.status_code != 200:\n",
" print(f\"Failed to fetch the website, {url}. Status Code: {response.status_code}\")\n",
" return\n",
" \n",
" filename = urlparse(url).path.strip(\"/\").replace(\"/\", \"_\") or \"home\"\n",
" filepath = f\"{data_path_rev}/{filename}.txt\"\n",
"\n",
" soup = BeautifulSoup(response.content, 'html.parser')\n",
" rev_content = soup.find('div', class_='entry-content')\n",
"\n",
" excluded_classes = [\n",
" \"custom-related-products-title\",\n",
" \"custom-related-products\",\n",
" \"has-white-color\"\n",
" ]\n",
"\n",
" content_divs = [\n",
" child for child in rev_content.find_all('div', recursive=False)\n",
" if not any(cls in child.get('class', []) for cls in excluded_classes)\n",
" ]\n",
"\n",
"\n",
" if not rev_content:\n",
" print(f\"No entry-content found in {url}\")\n",
" return\n",
" \n",
" with open(filepath, \"w\", encoding=\"utf-8\") as f:\n",
" f.write(f\"Source URL: {url}\\n\\n\")\n",
" for div in content_divs:\n",
" tags = div.find_all(lambda tag: (\n",
" tag.name in ['h1', 'h2', 'p'] or\n",
" (tag.name == 'div' and 'uagb-tm__desc' in tag.get('class', []))\n",
" ))\n",
" for tag in tags:\n",
" text = tag.get_text(strip=False)\n",
" if text:\n",
" f.write(f'{text}\\n')"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Crawling: https://aurowellness.com/glutathione-revolution/\n"
]
}
],
"source": [
"revolution_crawl('https://aurowellness.com/glutathione-revolution/')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|