File size: 9,042 Bytes
4aa3246 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"import pandas as pd\n",
"import os\n",
"import logging\n",
"import csv"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"class GoodReadsScrapper:\n",
" def __init__(self) -> None:\n",
" self.BASE_URL = 'https://www.goodreads.com/shelf/show/{}'\n",
" self.GENRE_URL = 'https://www.goodreads.com/genres/list?page={}'\n",
" self.GOOD_READS_URL = 'https://www.goodreads.com{}'\n",
" self.CURRENT_INDEX = 0\n",
" \n",
" def scrape_genres(self,filename='genres.txt'):\n",
" if os.path.exists(filename):\n",
" with open(filename, 'r') as file:\n",
" genres = [line.strip() for line in file.readlines()]\n",
" print(\"Genres loaded from file.\")\n",
" else:\n",
" page = 1\n",
" genres = []\n",
"\n",
" while True:\n",
" url = self.GENRE_URL.format(page)\n",
" response = requests.get(url)\n",
"\n",
" if response.status_code == 200:\n",
" soup = BeautifulSoup(response.text, 'html.parser')\n",
" container_div = soup.find('div', {'class': 'leftContainer'})\n",
" genre_divs = container_div.find_all('div', {'class': 'left'})\n",
" for genre_div in genre_divs:\n",
" genre = genre_div.find('a', {'class': 'mediumText actionLinkLite'})\n",
" if genre:\n",
" genre_text = genre.text.strip()\n",
" genres.append(genre_text)\n",
" print(\"Scrapped genre is:\", genre_text)\n",
"\n",
" next_page_link = soup.find('a', {'class': 'next_page'})\n",
" if next_page_link is None:\n",
" break\n",
"\n",
" page += 1\n",
"\n",
" with open(filename, 'w') as file:\n",
" for genre in genres:\n",
" file.write(genre + '\\n')\n",
" print(\"Genres saved to file.\")\n",
"\n",
" return genres\n",
" \n",
" def scrape_book(self,genre: str, csv_index: int):\n",
" response = requests.get(self.BASE_URL.format(genre))\n",
" \n",
" if response.status_code == 200:\n",
" soup = BeautifulSoup(response.text, 'html.parser')\n",
" container_div = soup.find('div', {'class': 'leftContainer'}) \n",
" book_divs = container_div.findAll('div', {'class': 'elementList'})\n",
" \n",
" for book_div in book_divs:\n",
" link = book_div.find('div', {'class': 'left'}).find('a', {'class': 'leftAlignedImage'})['href']\n",
" self.CURRENT_INDEX += 1\n",
" \n",
" if self.CURRENT_INDEX <= csv_index:\n",
" continue\n",
" \n",
" self.scrape_x_book(link,self.CURRENT_INDEX)\n",
" \n",
" def scrape_x_book(self,book_url: str, i: int):\n",
" try:\n",
" response = requests.get(self.GOOD_READS_URL.format(book_url))\n",
"\n",
" if response.status_code != 200:\n",
" logging.error(f\"Failed to fetch {book_url}. Status code: {response.status_code}\")\n",
" return\n",
"\n",
" soup = BeautifulSoup(response.text, 'html.parser')\n",
"\n",
" main_content = soup.find('div', {'class': 'BookPage__mainContent'})\n",
"\n",
" # Get title\n",
" title = main_content.find('div', {'class': 'BookPageTitleSection'}).find('div', {'class': 'BookPageTitleSection__title'}).find('h1', {'class': 'Text Text__title1'}).text.strip()\n",
"\n",
" # Metadata\n",
" metadata_section = main_content.find('div', {'class': 'BookPageMetadataSection'})\n",
"\n",
" # Author\n",
" author = metadata_section.find('div', {'class': 'BookPageMetadataSection__contributor'}).find('span', {'class': 'ContributorLink__name'}).text.strip()\n",
"\n",
" # Rating\n",
" rating = metadata_section.find('div', {'class': 'BookPageMetadataSection__ratingStats'}).find('div', {'class': 'RatingStatistics__column'}).find('div', {'class': 'RatingStatistics__rating'}).text.strip()\n",
"\n",
" # Description\n",
" description = metadata_section.find('div', {'class': 'BookPageMetadataSection__description'}).find('div', {'class': 'TruncatedContent'}).find('span', {'class': 'Formatted'}).text.strip()\n",
"\n",
" # Genres List\n",
" genres_list = []\n",
" genre_div = metadata_section.find('div', {'class': 'BookPageMetadataSection__genres'}).find('ul', {'class': 'CollapsableList'}).findAll('span', {'class': 'BookPageMetadataSection__genreButton'})\n",
"\n",
" for genre in genre_div:\n",
" g = genre.find('span', {'class': 'Button__labelItem'}).text.strip()\n",
" genres_list.append(g)\n",
"\n",
" # Get Reviews\n",
" reviews = []\n",
" reviews_section = soup.find('div', {'class': 'ReviewsSection'}).findAll('div', {'class': 'ReviewsList'})\n",
" articles = reviews_section[1].findAll('article', {'class': 'ReviewCard'})\n",
"\n",
" for article in articles:\n",
" review_text = article.find('section', {'class': 'ReviewText'}).find('span', {'class': 'Formatted'}).text.strip()\n",
" reviews.append(review_text)\n",
"\n",
" # Write to CSV\n",
" csv_filename = 'book_data.csv'\n",
" with open(csv_filename, 'a', newline='', encoding='utf-8') as csvfile:\n",
" fieldnames = ['Id', 'Title', 'Author', 'Rating', 'Description', 'Genres', 'Reviews']\n",
" writer = csv.DictWriter(csvfile, fieldnames=fieldnames)\n",
"\n",
" # If the file is empty, write the header\n",
" if csvfile.tell() == 0:\n",
" writer.writeheader()\n",
"\n",
" writer.writerow({\n",
" 'Id': i,\n",
" 'Title': title,\n",
" 'Author': author,\n",
" 'Rating': rating,\n",
" 'Description': description,\n",
" 'Genres': ', '.join(genres_list),\n",
" 'Reviews': '\\n'.join(reviews)\n",
" })\n",
"\n",
" # Log the processed book\n",
" print(f\"Processed book: {title} \\nRecord: {i}\")\n",
"\n",
" except Exception as e:\n",
" logging.error(f\"Error processing book {i}: {e}\")\n",
" # Optionally, you can log the error and continue to the next book\n",
"\n",
" def get_last_processed_id(self, csv_filename='book_data.csv'):\n",
" try:\n",
" if os.path.exists(csv_filename):\n",
" df = pd.read_csv(csv_filename)\n",
" if not df.empty and 'Id' in df.columns:\n",
" return df['Id'].max()\n",
" except pd.errors.EmptyDataError:\n",
" # Handle the case where the file is empty\n",
" return 0\n",
" except Exception as e:\n",
" # Handle other exceptions\n",
" print(f\"Error reading CSV file: {e}\")\n",
" \n",
" return 0\n",
" \n",
" def main(self):\n",
" genres = self.scrape_genres()\n",
" last_processed_id = self.get_last_processed_id()\n",
" for genre in genres:\n",
" self.scrape_book(genre, last_processed_id)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"scrapper = GoodReadsScrapper()\n",
"scrapper.main()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "venv",
"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": "3.9.6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|