Spaces:
Running
Running
File size: 10,930 Bytes
0ade82b |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#Requirements\n",
"#pip3 install requests\n",
"#pip3 install bs4"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Basic fundamentals of web scraping"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"this is with html tags : <title>Easy Python – A programming language of revolution</title>\n",
"this is without html tags: Easy Python\n",
"<a class=\"screen-reader-text skip-link\" href=\"#content\">Skip to content</a>\n"
]
}
],
"source": [
"# import these two modules bs4 for selecting HTML tags easily\n",
"from bs4 import BeautifulSoup\n",
"# requests module is easy to operate some people use urllib but I prefer this one because it is easy to use.\n",
"import requests\n",
"\n",
"# I put here my own blog url ,you can change it.\n",
"url=\"https://getpython.wordpress.com/\"\n",
"\n",
"#Requests module use to data from given url\n",
"source=requests.get(url)\n",
"\n",
"# BeautifulSoup is used for getting HTML structure from requests response.(craete your soup)\n",
"soup=BeautifulSoup(source.text,'html')\n",
"\n",
"# Find function is used to find a single element if there are more than once it always returns the first element.\n",
"title=soup.find('title') # place your html tagg in parentheses that you want to find from html.\n",
"print(\"this is with html tags :\",title)\n",
"\n",
"qwery=soup.find('h1') # here i find first h1 tagg in my website using find operation.\n",
"\n",
"#use .text for extract only text without any html tags\n",
"print(\"this is without html tags:\",qwery.text) \n",
"\n",
"\n",
"links=soup.find('a') #i extarcted link using \"a\" tag\n",
"print(links)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## extarct data from innerhtml "
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"#content\n"
]
}
],
"source": [
"# here i extarcted href data from anchor tag.\n",
"print(links['href']) "
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['screen-reader-text', 'skip-link']\n"
]
}
],
"source": [
"# similarly i got class details from a anchor tag\n",
"print(links['class'])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## findall operation in Bs4"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"total links in my website : 37\n",
"\n",
"<a class=\"screen-reader-text skip-link\" href=\"#content\">Skip to content</a>\n",
"<a href=\"https://getpython.wordpress.com/\" rel=\"home\">\n",
"<div class=\"cover\"></div>\n",
"</a>\n",
"<a class=\"screen-reader-text search-toggle\" href=\"#search-container\">Search</a>\n",
"<a href=\"https://getpython.wordpress.com/\" rel=\"home\">Easy Python</a>\n",
"<a aria-current=\"page\" href=\"/\">Home</a>\n",
"<a href=\"https://getpython.wordpress.com/contact/\">Contact</a>\n"
]
}
],
"source": [
"# findall function is used to fetch all tags at a single time.\n",
"many_link=soup.find_all('a') # here i extracted all the anchor tags of my website\n",
"total_links=len(many_link) # len function is use to calculate length of your array\n",
"print(\"total links in my website :\",total_links)\n",
"print()\n",
"for i in many_link[:6]: # here i use slicing to fetch only first 6 links from rest of them.\n",
" print(i)"
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<a href=\"https://getpython.wordpress.com/\" rel=\"home\">\n",
"<div class=\"cover\"></div>\n",
"</a>\n",
"\n",
"href is : https://getpython.wordpress.com/\n"
]
}
],
"source": [
"second_link=many_link[1] #here i fetch second link which place on 1 index number in many_links.\n",
"print(second_link)\n",
"print()\n",
"print(\"href is :\",second_link['href']) #only href link is extracted from ancor tag\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<div class=\"cover\"></div>\n",
"\n",
"['cover']\n",
"<class 'list'>\n",
"\n",
"class name of div is : cover\n"
]
}
],
"source": [
"# select div tag from second link\n",
"nested_div=second_link.find('div')\n",
"# As you can see div element extarcted , it also have inner elements\n",
"print(nested_div)\n",
"print()\n",
"#here i extracted class element from div but it give us in the form of list\n",
"z=(nested_div['class'])\n",
"print(z)\n",
"print(type(z))\n",
"print()\n",
"# \" \" .join () method use to convert list type into string type\n",
"print(\"class name of div is :\",\" \".join(nested_div['class'])) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## scrap data from wikipedia"
]
},
{
"cell_type": "code",
"execution_count": 60,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<title>World War II - Wikipedia</title>\n"
]
}
],
"source": [
"wiki=requests.get(\"https://en.wikipedia.org/wiki/World_War_II\")\n",
"soup=BeautifulSoup(wiki.text,'html')\n",
"print(soup.find('title'))\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### find html tags with classes"
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Contents\n",
"\n",
"1 Chronology\n",
"2 Background\n",
"\n",
"2.1 Europe\n",
"2.2 Asia\n",
"\n",
"\n",
"3 Pre-war events\n",
"\n",
"3.1 Italian invasion of Ethiopia (1935)\n",
"3.2 Spanish Civil War (1936–1939)\n",
"3.3 Japanese invasion of China (1937)\n",
"3.4 Soviet–Japanese border conflicts\n",
"3.5 European occupations and agreements\n",
"\n",
"\n",
"4 Course of the war\n",
"\n",
"4.1 War breaks out in Europe (1939–40)\n",
"4.2 Western Europe (1940–41)\n",
"4.3 Mediterranean (1940–41)\n",
"4.4 Axis attack on the Soviet Union (1941)\n",
"4.5 War breaks out in the Pacific (1941)\n",
"4.6 Axis advance stalls (1942–43)\n",
"\n",
"4.6.1 Pacific (1942–43)\n",
"4.6.2 Eastern Front (1942–43)\n",
"4.6.3 Western Europe/Atlantic and Mediterranean (1942–43)\n",
"\n",
"\n",
"4.7 Allies gain momentum (1943–44)\n",
"4.8 Allies close in (1944)\n",
"4.9 Axis collapse, Allied victory (1944–45)\n",
"\n",
"\n",
"5 Aftermath\n",
"6 Impact\n",
"\n",
"6.1 Casualties and war crimes\n",
"6.2 Genocide, concentration camps, and slave labour\n",
"6.3 Occupation\n",
"6.4 Home fronts and production\n",
"6.5 Advances in technology and warfare\n",
"\n",
"\n",
"7 See also\n",
"8 Notes\n",
"9 Citations\n",
"10 References\n",
"11 External links\n",
"\n",
"\n"
]
}
],
"source": [
"ww2_contents=soup.find_all(\"div\",class_='toc')\n",
"for i in ww2_contents:\n",
" print(i.text)"
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"World War II(clockwise from top left)\n",
"Chinese forces in the Battle of Wanjialing\n",
"Australian 25-pounder guns during the First Battle of El Alamein\n",
"German Stuka dive bombers on the Eastern Front in December 1943\n",
"American naval force in the Lingayen Gulf\n",
"Wilhelm Keitel signing the German Instrument of Surrender\n",
"Soviet troops in the Battle of Stalingrad\n",
"Date1 September 1939 – 2 September 1945 (1939-09-01 – 1945-09-02)(6 years and 1 day)[a]LocationEurope, Pacific, Atlantic, South-East Asia, China, Middle East, Mediterranean, North Africa, Horn of Africa, Australia, briefly North and South AmericaResult\n",
"Allied victory\n",
"Collapse of Nazi Germany\n",
"Fall of the Japanese and Italian Empires\n",
"Beginning of the Nuclear Age\n",
"Dissolution of the League of Nations\n",
"Creation of the United Nations\n",
"Emergence of the United States and the Soviet Union as rival superpowers\n",
"Beginning of the Cold War (more...)Participants\n",
"Allies\n",
"AxisCommanders and leaders\n",
"Main Allied leaders\n",
" Joseph Stalin\n",
" Franklin D. Roosevelt\n",
" Winston Churchill\n",
" Chiang Kai-shek\n",
"\n",
"Main Axis leaders\n",
" Adolf Hitler\n",
" Hirohito\n",
" Benito Mussolini\n",
"Casualties and losses\n",
"\n",
"Military dead:\n",
"Over 16,000,000\n",
"Civilian dead:\n",
"Over 45,000,000\n",
"Total dead:\n",
"Over 61,000,000\n",
"(1937–1945)\n",
"...further details\n",
"\n",
"\n",
"Military dead:\n",
"Over 8,000,000\n",
"Civilian dead:\n",
"Over 4,000,000\n",
"Total dead:\n",
"Over 12,000,000\n",
"(1937–1945)\n",
"...further details\n",
"\n"
]
}
],
"source": [
"overview=soup.find_all('table',class_='infobox vevent')\n",
"for z in overview:\n",
" print(z.text)\n",
" "
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.5.2"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|