Python爬取新闻网站保存标题、内容、日期、图片等数据(1)

{article}

“”"

def save_article(article, title):

html_path = ‘重庆新闻\’ + title + ‘.html’

pdf_path = ‘重庆新闻pdf\’ + title + ‘.pdf’

html = html_str.format(article=article)

with open(html_path, mode=‘w’, encoding=‘utf-8’) as f:

f.write(html)

print(‘{}已下载完成’.format(title))

exe 文件存放的路径

config = pdfkit.configuration(wkhtmltopdf=‘C:\Program Files\wkhtmltopdf\bin\wkhtmltopdf.exe’)

把 html 通过 pdfkit 变成 pdf 文件

pdfkit.from_file(html_path, pdf_path, configuration=config)

• 保存csv文件

f = open(‘新闻.csv’, mode=‘a’, encoding=‘utf-8-sig’, newline=‘’)

csv_writer = csv.DictWriter(f, fieldnames=[‘标题’, ‘作者’, ‘日期’, ‘新闻详情页’])

csv_writer.writeheader()

• 保存图片

def save_img(img_urls):

for i in img_urls:

img_url = ‘http://news.cqu.edu.cn’ + i

img_content = get_html(img_url).content

img_name = img_url.split(‘/’)[-1]

with open(‘新闻图片\’ + img_name, mode=‘wb’) as f:

f.write(img_content)

• 主函数

def main(url):

html_data = get_html(url).text

selector = get_pars(html_data)

lis = selector.css(‘body > div:nth-child(4) > div > div.lists .title a::attr(href)’).getall()

for li in lis:

content_data = get_html(li).text

li_selector = get_pars(co