Web crawler

booksTop250.py

import requests
from bs4 import BeautifulSoup
import codecs

DOWNLOAD_URL = 'http://book.douban.com/top250/'


def download_page(url):
    data = requests.get(url).content
    return data


def parse_html(html):
    soup = BeautifulSoup(html)
    book_list_soup = soup.find('div', attrs={'class': 'indent'})

    book_name_list = []

    for book_li in book_list_soup.find_all('table'):
        detail = book_li.find('div', attrs={'class': 'pl2'})
        book_name = detail.find('a').getText(strip=True)
        book_name_list.append(book_name)

    next_page = soup.find('span', attrs={'class': 'next'}).find('a')
    if next_page:
        return book_name_list, next_page['href']
    return book_name_list, None


def main():
    url = DOWNLOAD_URL

    with codecs.open('books', 'wb', encoding='utf-8') as fp:
        while url:
            html = download_page(url)
            books, url = parse_html(html)
            fp.write(u'{books}\n'.format(books='\n'.join(books)))


if __name__ == '__main__':
    main()

moviesTop250.py

import codecs

import requests
from bs4 import BeautifulSoup

DOWNLOAD_URL = 'http://movie.douban.com/top250/'


def download_page(url):
    data = requests.get(url).content
    return data


def parse_html(html):
    soup = BeautifulSoup(html)
    move_list_soup = soup.find('ol', attrs={'class': 'grid_view'})

    movie_name_list = []

    for movie_li in move_list_soup.find_all('li'):
        detail = movie_li.find('div', attrs={'class': 'hd'})
        movie_name = detail.find('span', attrs={'class': 'title'}).getText()
        movie_name_list.append(movie_name)

    next_page = soup.find('span', attrs={'class': 'next'}).find('a')
    if next_page:
        return movie_name_list, DOWNLOAD_URL + next_page['href']
    return movie_name_list, None


def main():
    url = DOWNLOAD_URL

    with codecs.open('movies', 'wb', encoding='utf-8') as fp:
        while url:
            html = download_page(url)
            movies, url = parse_html(html)
            fp.write(u'{movies}\n'.format(movies='\n'.join(movies)))


if __name__ == '__main__':
    main()

Python for Web crawler

• 豆瓣图书Top250 bookTop250.py
• 豆瓣电影Top250 moviesTop250.py