python爬虫——爬取快读小说app

1. 爬取结果（csv文件，出现了有两个表头…不明所以，无关大雅）

2. 使用fiddler4进行抓包


通过观察url，我们不难发现其中的规律，要实现进行分类抓取，需要更改url第一个数字，如下
https://sc.canrike.com/Categories/1/hot/1.html
https://sc.canrike.com/Categories/2/hot/1.html
要实现翻页需要更改url的最后一个数字，如下
https://sc.canrike.com/Categories/2/hot/1.html
https://sc.canrike.com/Categories/2/hot/2.html
要实现抓取某个分类中的分类（就是最热，最新，榜单，完结），需要修改url的关键字

3. 先抓取分类里面的Id

# 构建请求头
headers = {
    'Accept-Language': 'zh-CN,zh;q=0.8',
    'User-Agent': 'okhttp-okgo/jeasonlzy',
    'Content-Type': 'application/json',
    'Host': 'sc.canrike.com',
    'Connection': 'Keep-Alive',
    'Accept-Encoding': 'gzip',
}


# 抓取Id
def get_Id():
    url = 'https://sc.canrike.com/BookCategory.html'
    # 请求url，返回的数据是json格式
    resp = requests.get(url, headers=headers).json()
    # 判断resp是否存在
    if resp:
        # 取出返回json数据里面的data键值对，data是一个列表
        # 里面有我们需要的Id，通过Id来获取后面我们需要的信息
        Ids = resp.get('data')
        for temp in Ids:
            Id = temp.get('Id')
            yield Id

4. 先写获取最热书籍的信息，后面最新，榜单，完结的都是一样的代码，只需要更改url里面的关键字（比如hot,new,vote,over这些）。

# 获取最热的书籍信息
def get_hot_info(Id):
    page = 1
    while True:
        time.sleep(1)
        url = 'https://sc.canrike.com/Categories/{0}/hot/{1}.html'.format(Id, page)
        resp = requests.get(url, headers=headers)
        if resp.status_code == 200:
            try:
                data = json.loads(resp.content.decode('utf-8-sig'))
                BookLists = data.get('data').get('BookList')
                if BookLists:
                    for BookList in BookLists:
                        data_dict = {}

                        data_dict['Id'] = BookList.get('Id')
                        data_dict['Name'] = BookList.get('Name')
                        data_dict['Author'] = BookList.get('Author')
                        data_dict['CName'] = BookList.get('CName')
                        data_dict['Score'] = BookList.get('Score')
                        data_dict['Desc'] = BookList.get('Desc').replace('\u3000', '').replace('\r\n', '')

                        # 实时保存文件
                        title = data_dict.keys()
                        with open('快读小说.csv', 'a+', encoding='utf-8-sig', newline='') as f:
                            writer = csv.DictWriter(f, title)
                            writer.writerow(data_dict)

                        print(data_dict)
                page += 1
            except Exception as e:
                page += 1
                continue
        else:
            print('到底了')
            break

5. 上一步的函数里面有个实时保存数据，先在main函数写上表头，不然的话csv文件没表头就不知道你保存的信息分别是啥了。

def main():

    # 先对csv文件写入表头，后面就不需要在写了
    title = ['Id', 'Name', 'Author', 'Cname', 'Score', 'Desc']
    with open('快读小说.csv', 'a+', encoding='utf-8-sig', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(title)
    print('表头写入完成， 开始爬取数据')

    for Id in get_Id():
        get_hot_info(Id)
        get_new_info(Id)
        get_vote_info(Id)
        get_over_info(Id)

    print('爬取完成')

6. 全部代码附上

import requests
import json
import csv
import time


# 构建请求头
headers = {
    'Accept-Language': 'zh-CN,zh;q=0.8',
    'User-Agent': 'okhttp-okgo/jeasonlzy',
    'Content-Type': 'application/json',
    'Host': 'sc.canrike.com',
    'Connection': 'Keep-Alive',
    'Accept-Encoding': 'gzip',
}


# 抓取Id
def get_Id():
    url = 'https://sc.canrike.com/BookCategory.html'
    # 请求url，返回的数据是json格式
    resp = requests.get(url, headers=headers).json()
    # 判断resp是否存在
    if resp:
        # 取出返回json数据里面的data键值对，data是一个列表
        # 里面有我们需要的Id，通过Id来获取后面我们需要的信息
        Ids = resp.get('data')
        for temp in Ids:
            Id = temp.get('Id')
            yield Id


# 获取最热的书籍信息
def get_hot_info(Id):
    page = 1
    while True:
        time.sleep(1)
        url = 'https://sc.canrike.com/Categories/{0}/hot/{1}.html'.format(Id, page)
        resp = requests.get(url, headers=headers)
        if resp.status_code == 200:
            try:
                data = json.loads(resp.content.decode('utf-8-sig'))
                BookLists = data.get('data').get('BookList')
                if BookLists:
                    for BookList in BookLists:
                        data_dict = {}

                        data_dict['Id'] = BookList.get('Id')
                        data_dict['Name'] = BookList.get('Name')
                        data_dict['Author'] = BookList.get('Author')
                        data_dict['CName'] = BookList.get('CName')
                        data_dict['Score'] = BookList.get('Score')
                        data_dict['Desc'] = BookList.get('Desc').replace('\u3000', '').replace('\r\n', '')

                        # 实时保存文件
                        title = data_dict.keys()
                        with open('快读小说.csv', 'a+', encoding='utf-8-sig', newline='') as f:
                            writer = csv.DictWriter(f, title)
                            writer.writerow(data_dict)

                        print(data_dict)
                page += 1
            except Exception as e:
                page += 1
                continue
        else:
            print('到底了')
            break


# 获取最新的书籍信息
def get_new_info(Id):
    page = 1
    while True:
        time.sleep(1)
        url = 'https://sc.canrike.com/Categories/{0}/new/{1}.html'.format(Id, page)
        resp = requests.get(url, headers=headers)
        if resp.status_code == 200:
            try:
                data = json.loads(resp.content.decode('utf-8-sig'))
                BookLists = data.get('data').get('BookList')
                if BookLists:
                    for BookList in BookLists:
                        data_dict = {}

                        data_dict['Id'] = BookList.get('Id')
                        data_dict['Name'] = BookList.get('Name')
                        data_dict['Author'] = BookList.get('Author')
                        data_dict['CName'] = BookList.get('CName')
                        data_dict['Score'] = BookList.get('Score')
                        data_dict['Desc'] = BookList.get('Desc').replace('\u3000', '').replace('\r\n', '')

                        # 实时保存文件
                        title = data_dict.keys()
                        with open('快读小说.csv', 'a+', encoding='utf-8-sig', newline='') as f:
                            writer = csv.DictWriter(f, title)
                            writer.writerow(data_dict)

                        print(data_dict)
                page += 1
            except Exception as e:
                page += 1
                continue
        else:
            print('到底了')
            break


# 获取榜单的书籍信息
def get_vote_info(Id):
    page = 1
    while True:
        time.sleep(1)
        url = 'https://sc.canrike.com/Categories/{0}/vote/{1}.html'.format(Id, page)
        resp = requests.get(url, headers=headers)
        if resp.status_code == 200:
            try:
                data = json.loads(resp.content.decode('utf-8-sig'))
                BookLists = data.get('data').get('BookList')
                if BookLists:
                    for BookList in BookLists:
                        data_dict = {}

                        data_dict['Id'] = BookList.get('Id')
                        data_dict['Name'] = BookList.get('Name')
                        data_dict['Author'] = BookList.get('Author')
                        data_dict['CName'] = BookList.get('CName')
                        data_dict['Score'] = BookList.get('Score')
                        data_dict['Desc'] = BookList.get('Desc').replace('\u3000', '').replace('\r\n', '')

                        # 实时保存文件
                        title = data_dict.keys()
                        with open('快读小说.csv', 'a+', encoding='utf-8-sig', newline='') as f:
                            writer = csv.DictWriter(f, title)
                            writer.writerow(data_dict)

                        print(data_dict)
                page += 1
            except Exception as e:
                page += 1
                continue
        else:
            print('到底了')
            break


# 获取完结的书籍信息
def get_over_info(Id):
    page = 1
    while True:
        time.sleep(1)
        url = 'https://sc.canrike.com/Categories/{0}/over/{1}.html'.format(Id, page)
        resp = requests.get(url, headers=headers)
        if resp.status_code == 200:
            try:
                data = json.loads(resp.content.decode('utf-8-sig'))
                BookLists = data.get('data').get('BookList')
                if BookLists:
                    for BookList in BookLists:
                        data_dict = {}

                        data_dict['Id'] = BookList.get('Id')
                        data_dict['Name'] = BookList.get('Name')
                        data_dict['Author'] = BookList.get('Author')
                        data_dict['CName'] = BookList.get('CName')
                        data_dict['Score'] = BookList.get('Score')
                        data_dict['Desc'] = BookList.get('Desc').replace('\u3000', '').replace('\r\n', '')

                        # 实时保存文件
                        title = data_dict.keys()
                        with open('快读小说.csv', 'a+', encoding='utf-8-sig', newline='') as f:
                            writer = csv.DictWriter(f, title)
                            writer.writerow(data_dict)

                        print(data_dict)
                page += 1
            except Exception as e:
                page += 1
                continue
        else:
            print('到底了')
            break


def main():

    # 先对csv文件写入表头，后面就不需要在写了
    title = ['Id', 'Name', 'Author', 'Cname', 'Score', 'Desc']
    with open('快读小说.csv', 'a+', encoding='utf-8-sig', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(title)
    print('表头写入完成， 开始爬取数据')

    for Id in get_Id():
        get_hot_info(Id)
        get_new_info(Id)
        get_vote_info(Id)
        get_over_info(Id)

    print('爬取完成')


if __name__ == '__main__':

    main()