Python 7 个网络爬虫实战案例及源码解析

Python 7 个网络爬虫实战案例及源码解析 | 极客日志

import requests
from bs4 import BeautifulSoup
import csv

# 请求 URL
url = 'https://movie.douban.com/top250'
# 请求头部
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

# 解析页面函数
def parse_html(html):
    soup = BeautifulSoup(html, 'lxml')
    movie_list = soup.find('ol', class_='grid_view').find_all('li')
    for movie in movie_list:
        title = movie.find('div', class_='hd').find('span', class_='title').get_text()
        rating_num = movie.find('div', class_='star').find('span', class_='rating_num').get_text()
        comment_num = movie.find('div', class_='star').find_all('span')[-1].get_text()
        writer.writerow([title, rating_num, comment_num])

# 保存数据函数
def save_data():
    f = open('douban_movie_top250.csv', 'a', newline='', encoding='utf-8-sig')
    global writer
    writer = csv.writer(f)
    writer.writerow(['电影名称', '评分', '评价人数'])
    for i in range(10):
        url = 'https://movie.douban.com/top250?start=' + str(i*25) + '&filter='
        response = requests.get(url, headers=headers)
        parse_html(response.text)
    f.close()

if __name__ == '__main__':
    save_data()

import requests
import re

# 请求 URL
url = 'https://maoyan.com/board/4'
# 请求头部
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

# 解析页面函数
def parse_html(html):
    pattern = re.compile('<p class="name"><a href=".*?" title="(.*?)" data-act="boarditem-click" data-val="{movieId:\\d+}">(.*?)</a></p>.*?<p class="star">(.*?)</p>.*?<p class="releasetime">(.*?)</p>', re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            '电影名称': item[1],
            '主演': item[2].strip(),
            '上映时间': item[3]
        }

# 保存数据函数
def save_data():
    f = open('maoyan_top100.txt', 'w', encoding='utf-8')
    for i in range(10):
        url = 'https://maoyan.com/board/4?offset=' + str(i*10)
        response = requests.get(url, headers=headers)
        for item in parse_html(response.text):
            f.write(str(item) + '\n')
    f.close()

if __name__ == '__main__':
    save_data()

import requests
import re

# 请求 URL
url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2019.html'
# 请求头部
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

# 解析页面函数
def parse_html(html):
    pattern = re.compile('<tr class="alt">.*?<td>(.*?)</td>.*?<td><div align="left">.*?<a href="(.*?)" target="_blank">(.*?)</a></div></td>.*?<td>(.*?)</td>.*?<td>(.*?)</td>.*?</tr>', re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            '排名': item[0],
            '学校名称': item[2],
            '省市': item[3],
            '总分': item[4]
        }

# 保存数据函数
def save_data():
    f = open('university_top100.txt', 'w', encoding='utf-8')
    response = requests.get(url, headers=headers)
    for item in parse_html(response.text):
        f.write(str(item) + '\n')
    f.close()

if __name__ == '__main__':
    save_data()

import requests
from lxml import etree
import csv

# 请求 URL
url = 'http://www.weather.com.cn/weather1d/101010100.shtml'
# 请求头部
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

# 解析页面函数
def parse_html(html):
    selector = etree.HTML(html)
    city = selector.xpath('//*[@id="around"]/div/div[1]/div[1]/h1/text()')[0]
    temperature = selector.xpath('//*[@id="around"]/div/div[1]/div[1]/p/i/text()')[0]
    weather = selector.xpath('//*[@id="around"]/div/div[1]/div[1]/p/@title')[0]
    wind = selector.xpath('//*[@id="around"]/div/div[1]/div[1]/p/span/text()')[0]
    return city, temperature, weather, wind

# 保存数据函数
def save_data():
    f = open('beijing_weather.csv', 'w', newline='', encoding='utf-8-sig')
    writer = csv.writer(f)
    writer.writerow(['城市', '温度', '天气', '风力'])
    for i in range(10):
        response = requests.get(url, headers=headers)
        city, temperature, weather, wind = parse_html(response.text)
        writer.writerow([city, temperature, weather, wind])
    f.close()

if __name__ == '__main__':
    save_data()

import requests
from lxml import etree
import csv

# 请求 URL
url = 'http://search.dangdang.com/?key=Python&act=input'
# 请求头部
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

# 解析页面函数
def parse_html(html):
    selector = etree.HTML(html)
    book_list = selector.xpath('//*[@id="search_nature_rg"]/ul/li')
    for book in book_list:
        title = book.xpath('a/@title')[0]
        link = book.xpath('a/@href')[0]
        price = book.xpath('p[@class="price"]/span[@class="search_now_price"]/text()')[0]
        author = book.xpath('p[@class="search_book_author"]/span[1]/a/@title')[0]
        publish_date = book.xpath('p[@class="search_book_author"]/span[2]/text()')[0]
        publisher = book.xpath('p[@class="search_book_author"]/span[3]/a/@title')[0]
        yield {
            '书名': title,
            '链接': link,
            '价格': price,
            '作者': author,
            '出版日期': publish_date,
            '出版社': publisher
        }

# 保存数据函数
def save_data():
    f = open('dangdang_books.csv', 'w', newline='', encoding='utf-8-sig')
    writer = csv.writer(f)
    writer.writerow(['书名', '链接', '价格', '作者', '出版日期', '出版社'])
    response = requests.get(url, headers=headers)
    for item in parse_html(response.text):
        writer.writerow(item.values())
    f.close()

if __name__ == '__main__':
    save_data()

import requests
from lxml import etree

# 请求 URL
url = 'https://www.qiushibaike.com/text/'
# 请求头部
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

# 解析页面函数
def parse_html(html):
    selector = etree.HTML(html)
    content_list = selector.xpath('//div[@class="content"]/span/text()')
    for content in content_list:
        yield content

# 保存数据函数
def save_data():
    f = open('qiushibaike_jokes.txt', 'w', encoding='utf-8')
    for i in range(3):
        url = 'https://www.qiushibaike.com/text/page/' + str(i+1) + '/'
        response = requests.get(url, headers=headers)
        for content in parse_html(response.text):
            f.write(content + '\n')
    f.close()

if __name__ == '__main__':
    save_data()

import time
from selenium import webdriver
import requests

# 请求 URL
url = 'https://weibo.com/'
# 请求头部
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

# 解析页面函数
def parse_html(html):
    print(html)

# 保存数据函数
def save_data():
    f = open('weibo.txt', 'w', encoding='utf-8')
    browser = webdriver.Chrome()
    browser.get(url)
    time.sleep(10)
    # 注意：生产环境请勿硬编码账号密码
    browser.find_element_by_name('username').send_keys('username')
    browser.find_element_by_name('password').send_keys('password')
    browser.find_element_by_class_name('W_btn_a').click()
    time.sleep(10)
    response = requests.get(url, headers=headers, cookies=browser.get_cookies())
    parse_html(response.text)
    browser.close()
    f.close()

if __name__ == '__main__':
    save_data()

Python 7 个网络爬虫实战案例及源码解析

Python 7 个网络爬虫实战案例及源码解析

1. 爬取豆瓣电影 Top250

2. 爬取猫眼电影 Top100

3. 爬取全国高校名单

4. 爬取中国天气网城市天气

5. 爬取当当网图书信息

6. 爬取糗事百科段子

7. 爬取新浪微博

注意事项与最佳实践

更多推荐文章

相关免费在线工具

Python 7 个网络爬虫实战案例及源码解析

Python 7 个网络爬虫实战案例及源码解析

1. 爬取豆瓣电影 Top250

2. 爬取猫眼电影 Top100

3. 爬取全国高校名单

4. 爬取中国天气网城市天气

5. 爬取当当网图书信息

6. 爬取糗事百科段子

7. 爬取新浪微博

注意事项与最佳实践

微信扫一扫，关注极客日志

更多推荐文章

相关免费在线工具