def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
if not response:
return None
selector = etree.HTML(response)
lis = selector.xpath("//div[@class='main']/div[@id='left']/ul[@class='app-list']//li")
return lis
def loop_request(self, lis, first_page=True, **kwargs):
"""循环请求"""
for li in lis:
if not li[1].xpath("div/p[@class='info']"):
continue
# app_name = self.get_app_name(li)
# app_name = self.judge_null(app_name)
# app_name = self.field_strip(app_name)
# enter_url = self.get_enter_url(li) # 获取详情页url
# inner_response = RqCompoent.get(enter_url, **self.add_headers)
# fields = self.parse_app_info_page(inner_response)
# to_sink = [app_name, *fields]
# print(*to_sink)
# sleep(self.delay_time)
enter_url = self.get_enter_url(li) # 获取详情页url
inner_response = RqCompoent.get(enter_url, **self.add_headers)
if inner_response:
self.inner_response = inner_response
self.li = li
app_name = self.get_app_name(li)
app_name = self.judge_null(app_name)
app_name = self.field_strip(app_name)
img_address = self.get_img_address(li)
app_intro = self.get_app_intro(inner_response)
fields = self.parse_app_info_page(inner_response)
to_sink = [self.name, app_name, *fields, img_address, app_intro]
print(*to_sink[:-1], to_sink[-1][:20])
sleep(self.delay_time)
def loop_request(self, lis, first_page=True, **kwargs):
"""循环请求"""
# for li in lis:
# app_name = self.get_app_name(li)
# app_name = self.judge_null(app_name)
# app_name = self.field_strip(app_name)
# enter_url = self.get_enter_url(li)
# # 如果 enter_url 不是以 .html 结尾，不要
# if not enter_url.endswith(".html"):
# continue
# inner_response = RqCompoent.get(enter_url)
# fields = self.parse_app_info_page(inner_response)
# to_sink = [app_name, *fields]
# print(*to_sink)
# # sleep(self.delay_time)
for li in lis:
enter_url = self.get_enter_url(li) # 获取详情页url
if not enter_url.endswith(".html"):
continue
inner_response = RqCompoent.get(enter_url, **self.add_headers)
if inner_response:
self.inner_response = inner_response
self.li = li
app_name = self.get_app_name(li)
app_name = self.judge_null(app_name)
app_name = self.field_strip(app_name)
img_address = self.get_img_address(li)
app_intro = self.get_app_intro(inner_response)
fields = self.parse_app_info_page(inner_response)
to_sink = [
self.name, app_name, *fields, img_address, app_intro
]
print(*to_sink[:-1], to_sink[-1][:20])
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(self.url)
self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath("//div[@class='result_box']//dl")
# print(lis)
return lis
def get_app_list_elements(self, url="http://s.5577.com") -> list:
response = RqCompoent.get(self.url)
self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath("//div[@class='g-left f-fl']//div[@class='m-cont-list']")
print(lis)
return lis
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath('//div[@class="m-solist"]//div')
# print(lis)
return lis
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
self.outer_response = response
selector = etree.HTML(response)
lis1 = selector.xpath('//dl[@id="result"]//dt')
lis2 = selector.xpath('//dl[@id="result"]//dd')
# print(lis)
return list(zip(lis1, lis2))
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
# print(response)
selector = etree.HTML(response)
lis = selector.xpath(
"//div[@class='main']/div[@class='SeaCon']/ul//li")
# print(lis)
return lis
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
response = re.findall(
"jQuery191018405249964393477_1594619120728\((.*?)\);", response,
re.S)[0]
big_dict = json.loads(response)
items = big_dict.get("data")
return items
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
selector = etree.HTML(response)
lis = selector.xpath("//ul[@class='MlistC']//li")
extra = selector.xpath("//ul[@class='MlistD']//li")
if extra:
lis.append(extra[0])
return lis
def run():
keyword = "支付"
driver = webdriver.Chrome()
driver.get("https://www.wandoujia.com/")
driver.maximize_window()
driver.implicitly_wait(6)
search_input = driver.find_element_by_xpath(
'//input[@class="key-ipt"]')
search_input.clear()
search_input.send_keys(keyword)
search_input.send_keys(Keys.ENTER)
driver.implicitly_wait(6)
# 切换到指定元素的位置
move_to = driver.find_element_by_partial_link_text("查看更多")
ActionChains(driver).move_to_element(move_to).perform()
move_to.click()
time.sleep(2)
driver.implicitly_wait(2)
page_source = driver.page_source
selector = etree.HTML(page_source)
enter_urls = selector.xpath('//h2[@class="app-title-h2"]/a/@href')
print(enter_urls)
# time.sleep(3)
driver.quit()
for enter_url in enter_urls:
response = RqCompoent.get(enter_url)
selector = etree.HTML(response)
app_name = judge_null(
selector.xpath('//span[@class="title"]/text()'))
download_url = judge_null(
selector.xpath('//div[@class="download-wp"]/a[2]/@href'))
update_time = judge_null(
selector.xpath('//span[@class="update-time"]/text()'))
if update_time:
update_time = update_time.split(":")[1].strip()
version = judge_null(
re.findall("版本</dt><dd>(.*?)<", response, re.S))
if version:
version = version.split(";")[1].strip()
author = judge_null(
re.findall("开发者</dt><dd><.*?>([\u4E00-\u9FA5]+)<", response,
re.S))
img = judge_null(
selector.xpath('//div[@class="app-icon"]/img/@src'))
intro = judge_null(
selector.xpath('string(//div[@class="desc-info"]/div/div)'))
print(app_name, download_url, update_time, version, author, img,
intro)
# 清洗一下，换一下顺序即可
row = [
"豌豆荚", app_name, version, update_time, author, download_url,
img, intro
]
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
# print(response)
self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath(
"//div[@id='center']/div[@id='results']//div[@class='result f s0']"
)
return lis
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
if not response:
return [None, None, None, None]
# big_dict = json.loads(response)
big_dict = demjson.decode(response)
items = list(zip(big_dict.get("SoftUrl"), big_dict.get("ResName"), \
big_dict.get("ResVer"), big_dict.get("UpdateTime"), big_dict.get("SmallImg")))
return items
def loop_request(self, items, first_page=True):
"""循环请求"""
if not items:
return
# # 爬第一页的所有app信息
# if not self.match_keyword:
for item in items:
try:
enter_url = self.get_enter_url(item) # 获取详情页url
except:
pass
if not enter_url:
continue
app_name = None
img_address = None
app_intro = None
try:
inner_response = RqCompoent.get(enter_url, **self.add_headers)
except:
inner_response = None
if inner_response:
self.item = item
self.inner_response = inner_response
try:
app_name = self.get_app_name(item) # 先获取一下app名字，对比关键字
except:
pass
# app_name = self.judge_null(app_name)
app_name = self.field_strip(app_name)
try:
img_address = self.get_img_address(item)
except:
pass
try:
app_intro = self.get_app_intro(inner_response)
except:
pass
fields = self.parse_app_info_page(inner_response, item)
to_sink = [self.name, app_name, *fields, img_address, app_intro]
res = []
for i in to_sink:
if not i:
res.append(None)
else:
res.append(pymysql.escape_string(i))
try:
print(*res[:-1], res[-1][:20])
except:
pass
sql = "insert into spider_app(appStore, appName, version, updateTime, author,downloadUrl,icon, introduction, inList, platform, insertTime, keyword, enter_url) values(%s, %s, %s, %s, %s, %s, %s, %s, '否', '安卓', %s, %s, %s)"
res = [*res, pymysql.escape_string(time.strftime("%Y/%m/%d", time.localtime())), pymysql.escape_string(self.keyword), pymysql.escape_string(enter_url)]
try:
self.cursor.execute(sql, res)
except:
pass
sleep(self.delay_time)
self.db.commit()
def get_app_list_elements(self, url) -> list:
"""
获取搜索结果列表对应的元素
:return: 搜索结果元素列表
"""
response = RqCompoent.get(url)
if not response:
return "error"
self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath()
return lis
def get_app_list_elements(
self,
url="https://www.52z.com/search?keyword=&s=1001&page=1&ajax=1"
) -> list:
print(self.url)
response = RqCompoent.get(self.url)
# self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath("body//li")
# print(lis)
return lis
def get_app_list_elements(
self,
url="https://s.pc6.com/cse/search?s=12026392560237532321&entry=1&ie=gbk&q="
) -> list:
print(self.url)
response = RqCompoent.get(self.url)
# self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath(
"body[@id='search']/div[@id='mbody']/div[@id='scont']/dl[@id='result']//dt"
)
# print(lis)
return lis
def get_app_list_elements(self, url) -> list:
"""
获取搜索结果列表对应的元素
:return: 搜索结果元素列表
"""
response = RqCompoent.get(url)
big_dict = json.loads(response)
print(big_dict)
items = []
# selector = etree.HTML(response)
# lis = selector.xpath()
# return lis
return items
def get_download_url(self, inner_response):
"""获取下载地址"""
another_response = RqCompoent.get(
"https://www.52z.com/soft/downview?id=" + self.app_id)
download_pat = 'http://(.*?)\.apk'
download_url = re.findall(download_pat, another_response, re.S)
if download_url:
download_url = download_url[0]
download_url = "http://" + download_url[0] + ".apk"
else:
download_url = []
# selector = etree.HTML(inner_response)
# download_url = selector.xpath("/html/body[@id='body']/div[@class='elywNei']/div[@class='elRight']/div[@class='elYxjsBox'][3]/div[@id='downajaxview']/div[@class='elYxxzIn'][1]/ul[@class='elYxxzList']/li[1]/a/@href")
# download_url = self.judge_null(download_url)
return download_url
def get_download_url(self, inner_response, li):
"""获取下载地址"""
# app_id_pat = 'opendown\((.*?)\);" title="下载到电脑"'
# app_id = re.findall(app_id_pat, inner_response)
# download_url = li.xpath("a/@apkurl")
# if download_url:
# download_url = download_url[0]
# download_url = "http://m.anzhuoapk.com" + download_url
res = None
try:
res = RqCompoent.get("http://zhushou.sogou.com/apps/download.html?appid={}".format(self.app_id))
except:
pass
if not res:
return None
j = json.loads(res)
download_url = j.get("data").get("file_url")
return download_url
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
selector = etree.HTML(response)
lis = selector.xpath('//ul[@class="app-list"]//li')
return lis
def loop_request(self, lis, first_page=True, **kwargs):
"""循环请求"""
if not lis:
return
# for li in lis:
# app_name = self.get_app_name(li) # 先获取一下app名字，对比关键字
# app_name = self.judge_null(app_name)
# app_name = self.field_strip(app_name)
# if first_page:
# if self.keyword == app_name:
# enter_url = self.get_enter_url(li) # 获取详情页url
# inner_response = RqCompoent.get(enter_url)
# fields = self.parse_app_info_page(inner_response)
# to_sink = [app_name, *fields]
# print(*to_sink)
# self.match_keyword = True
# break
# else:
# enter_url = self.get_enter_url(li) # 获取详情页url
# inner_response = RqCompoent.get(enter_url)
# fields = self.parse_app_info_page(inner_response)
# to_sink = [app_name, *fields]
# print(*to_sink)
# sleep(self.delay_time)
# # 爬第一页的所有app信息
# if not self.match_keyword:
# for li in lis:
# app_name = self.get_app_name(li) # 先获取一下app名字，对比关键字
# app_name = self.judge_null(app_name)
# app_name = self.field_strip(app_name)
# enter_url = self.get_enter_url(li) # 获取详情页url
# inner_response = RqCompoent.get(enter_url)
# fields = self.parse_app_info_page(inner_response)
# to_sink = [app_name, *fields]
# print(*to_sink)
# sleep(self.delay_time)
for li in lis:
enter_url = None
try:
enter_url = self.get_enter_url(li) # 获取详情页url
except:
pass
inner_response = RqCompoent.get(enter_url, **self.add_headers)
if inner_response:
self.inner_response = inner_response
self.li = li
app_name = None
img_address = None
app_intro = None
try:
app_name = self.get_app_name(li) # 先获取一下app名字，对比关键字
except:
pass
app_name = self.judge_null(app_name)
app_name = self.field_strip(app_name)
try:
img_address = self.get_img_address(li)
except:
pass
try:
app_intro = self.get_app_intro(inner_response)
except:
pass
fields = self.parse_app_info_page(inner_response)
to_sink = [
self.name, app_name, *fields, img_address, app_intro
]
res = []
for i in to_sink:
if not i:
res.append(None)
else:
res.append(pymysql.escape_string(i))
try:
print(*res[:-1], res[-1][:20])
except:
pass
sql = "insert into spider_app(appStore, appName, version, updateTime, author,downloadUrl,icon, introduction, inList, platform, insertTime, keyword, enter_url) values(%s, %s, %s, %s, %s, %s, %s, %s, '否', '安卓', %s, %s, %s)"
res = [
*res,
pymysql.escape_string(
time.strftime("%Y/%m/%d", time.localtime())),
pymysql.escape_string(self.keyword),
pymysql.escape_string(enter_url)
]
try:
self.cursor.execute(sql, res)
except:
pass
sleep(self.delay_time)
self.db.commit()
def get_app_list_elements(self,
url="https://s.liqucn.com/s.php?words=") -> list:
response = RqCompoent.get(self.url)
selector = etree.HTML(response)
lis = selector.xpath("//div[@class='sear_app']//dl")
return lis
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
selector = etree.HTML(response)
lis = selector.xpath("//div[@class='main-con']/div[@class='applist-wrap']/ul[@class='applist']//li")
return lis
def temp_request(self, enter_url, method="get", data={}):
if method == "get":
inner_response = RqCompoent.get(enter_url, **self.add_headers)
else:
inner_response = RqCompoent.post(
enter_url, data, **self.add_headers)
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
big_dict = json.loads(response)
items = big_dict.get("obj").get("items")
return items
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
if response:
big_dict = json.loads(response)
items = big_dict.get("data")
return items
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
selector = etree.HTML(response)
lis = selector.xpath("//div[@class='app_list border_three']/ul//li")
return lis
def get_app_list_elements(self, url) -> list:
response = RqCompoent.get(url)
self.outer_response = response
selector = etree.HTML(response)
lis = selector.xpath("//div[@class='listCont']/ul//li")
return lis