如何使用python web scraping从主页获取所有列表URL [英] How to get all listings urls from main page with python web scraping
本文介绍了如何使用python web scraping从主页获取所有列表URL的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!
问题描述
我写了一个用于Web抓取的代码,除了两个问题外,我的代码还可以.从详细信息页面来看,只是ISBN NO一切正常,从主页来看,我需要所有列表URL,以便我的代码可以从列表中获取日期.请指导我如何解决此问题. (主页面和详细信息页面)URL均在代码中.谢谢!
I wrote a code for web scraping, My code is ok just except two issues. From detail page, everything is ok just ISBN NO, and from main page, I need all listing URLs so that my code could scrape date from aa listings. Please guide me how can I fix this issue. Both(main page and details page )URLs are in the code. Thank you!
这是我的代码:
import requests
from bs4 import BeautifulSoup
import csv
def get_page(url):
response = requests.get(url)
if not response.ok:
print('server responded:', response.status_code)
else:
soup = BeautifulSoup(response.text, 'html.parser') # 1. html , 2. parser
return soup
def get_detail_data(soup):
try:
title = soup.find('span',class_="title product-field",id=False).text
except:
title = 'empty'
print(title)
try:
writer = soup.find('a',class_="contributor-name",id=False).text
except:
writer = 'empty'
print(writer)
try:
original_price = soup.find('div',class_="original-price",id=False).find('span').text
except:
original_price = 'empty'
print(original_price)
try:
active_price = soup.find('div',class_="active-price",id=False).find('span').text
except:
active_price = 'empty'
print(active_price)
try:
img = soup.find('div',class_="image-actions image-container product-type-icon-container book",id=False).find('img').attrs['src']
except:
img = 'empty'
print(img)
try:
isbn = soup.find('div',class_="bookitem-secondary-metadata",id=False).find('li').attrs['ISBN: ']
except:
isbn = 'empty'
print(isbn)
data = {
'title' : title,
'writer' : writer,
'original_price' : original_price,
'active_price' : active_price,
'image' : img,
'isbn' : isbn
}
return data
def get_index_data(soup):
titles_link = soup.find_all('a',class_="body_link_11")
try:
inks = soup.find('div', class_="item-info",id=False).find('p').find('a').get('href')
except:
inks = "empty"
print(inks)
def main():
#detail_page_url = "https://www.kobo.com/ww/en/ebook/mum-dad-1"
mainurl = "https://www.kobo.com/ww/en/list/new-hot-in-fiction/youL53408U25RHrVu3wR5Q"
#get_page(url)
#get_detail_data(get_page(detail_page_url))
get_index_data(get_page(mainurl))
if __name__ == '__main__':
main()
推荐答案
import requests
import re
import json
from bs4 import BeautifulSoup
import csv
def Soup(content):
soup = BeautifulSoup(content, 'html.parser')
return soup
def Main(url):
r = requests.get(url)
soup = Soup(r.content)
scripts = soup.findAll("script", type="application/ld+json",
text=re.compile("data"))
prices = [span.text for span in soup.select(
"p.product-field.price span span") if span.text != "USD"]
with open("data.csv", 'w', newline="") as f:
writer = csv.writer(f)
writer.writerow(["Title", "Writer", "Price", "ISBN", "IMG", "URL"])
for script, price in zip(scripts, prices):
script = json.loads(script.text)
title = script["data"]["name"]
author = script["data"]["author"][0]["name"]
img = f'https:{script["data"]["thumbnailUrl"]}'
isbn = script["data"]["isbn"]
url = script["data"]["url"]
writer.writerow([title, author, price, isbn, img, url])
Main("https://www.kobo.com/ww/en/list/new-hot-in-fiction/youL53408U25RHrVu3wR5Q")
输出:在线查看
输出样本:
这篇关于如何使用python web scraping从主页获取所有列表URL的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!
查看全文