python - 我的脚本有问题，无法抓取许多页面的数据

问题描述

我编写了一个代码来从多个页面中抓取数据（意味着包括分页）。除了下一页活动外，我的代码一切正常。我的代码只是抓取第一页的数据当我为下一页设置一个循环时，当它完成第一页数据时，它再次开始抓取第一页的数据并在我设置循环时继续抓取同一页的数据。实际上，我是使用 python 进行网络抓取的新手，所以请指导我。你能帮我修复我的代码吗？请看一下我的代码并帮助我，谢谢

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_page(soup):

     try:
        title = (soup.find('h1',class_="cdm_style",id=False).text)
     except:
         title = 'Empty Title'
     try:
         collection = (soup.find('td',id="metadata_collec").find('a').text)
     except:
         collection = "Empty Collection"
     try:
         author = (soup.find('td',id="metadata_creato").text)
     except:
         author = "Empty Author"
     try:
         abstract = (soup.find('td',id="metadata_descri").text)
     except:
         abstract = "Empty Abstract"
     try:
         keywords = (soup.find('td',id="metadata_keywor").text)
     except:
         keywords = "Empty Keywords"
     try:
         publishers = (soup.find('td',id="metadata_publis").text)
     except:
         publishers = "Empty Publishers"
     try:
         date_original = (soup.find('td',id="metadata_contri").text)
     except:
         date_original = "Empty Date original"
     try:
        date_digital = (soup.find('td',id="metadata_date").text)
     except:
        date_digital = "Empty Date digital"
     try:
        formatt = (soup.find('td',id="metadata_source").text)
     except:
        formatt = "Empty Format"
     try:
        release_statement = (soup.find('td',id="metadata_rights").text)
     except:
        release_statement = "Empty Realease Statement"
     try:
        library = (soup.find('td',id="metadata_librar").text)
     except:
        library = "Empty Library"
     try:
        date_created = (soup.find('td',id="metadata_dmcreated").text)
     except:
        date_created = "Empty date Created"
     data = {
         'Title'        : title.strip(),
         'Collection'   : collection.strip(),
         'Author'       : author.strip(),
         'Abstract'     : abstract.strip(),
         'Keywords'     : keywords.strip(),
         'Publishers'   : publishers.strip(),
         'Date_original': date_original.strip(),
         'Date_digital' : date_digital.strip(),
         'Format'       : formatt.strip(),
         'Release-st'   : release_statement.strip(),
         'Library'      : library.strip(),
         'Date_created' : date_created.strip()


     }
     return data
def get_index_data(soup):
    try:
        titles_link = soup.find_all('a',class_="body_link_11")
    except:
        titles_link = []
    else:
        titles_link_output = []
        for link in titles_link:
            try:
                item_id = link.attrs.get('item_id', None) #All titles with valid links will have an item_id
                if item_id:
                    titles_link_output.append("{}{}".format("http://cgsc.cdmhost.com",link.attrs.get('href', None)))
            except:
                continue
    return titles_link_output
def write_csv(data,url):
    with open('1111_to_5555.csv','a') as csvfile:
        writer = csv.writer(csvfile)
        row = [data['Title'], data['Collection'], data['Author'],
        data['Abstract'], data['Keywords'], data['Publishers'], data['Date_original'],
        data['Date_digital'], data['Format'], data['Release-st'], data['Library'],
        data['Date_created'], url]
        writer.writerow(row)
def main():
    for x in range(2,4):
        mainurl = ("http://cgsc.cdmhost.com/cdm/search/collection/p4013coll8/searchterm/1/field/all/mode/all/conn/and/order/nosort/page/")
        print(x)
        url = f"{mainurl}{x}"
        products = get_index_data(get_page(url))
        for product in products:
            data1 = get_detail_page(get_page(product))
            write_csv(data1,product)


if __name__ == '__main__':
    main()

标签： pythonweb-scrapingbeautifulsoupweb-crawler

python - 我的脚本有问题，无法抓取许多页面的数据

问题描述

解决方案

推荐阅读