class FileSystem:
def __init__(self):
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
def file_download(self, url, file_type, file_name=str(random.random())):
download_dir_path = "..\\download_files\\"
if not os.path.exists(download_dir_path):
os.mkdir(download_dir_path)
download_file_path = download_dir_path + file_name + file_type
if os.path.exists(download_file_path):
return
try_count = 0
while True:
try:
download_file_path = download_dir_path + str(
random.random()) + file_type
# html_analyse = HtmlAnalyse(url, proxy=self.proxy_ip)
html_analyse = HtmlAnalyse(url)
html_analyse.download(download_file_path)
print("File Download Success !!")
break
except Exception as e:
print(sys._getframe().f_code.co_name, url, e)
try_count += 1
if try_count > 2 and "https" in url:
return
if try_count > 5:
return
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
# download_file_path = download_dir_path + str(random.random()) + file_type
return download_file_path
def file_upload(self, local_file_path):
if not local_file_path:
return
while True:
try:
with open(local_file_path, "rb") as f:
res = requests.post(File_Server_Url, files={'file': f})
if res.status_code == 200:
res_j = res.json()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
server_file_path = res_j["path"]
print("File Server Upload Success !!")
return server_file_path
def download_upload(self, url, file_type):
download_file_path = self.file_download(url, file_type)
server_file_path = self.file_upload(download_file_path)
return server_file_path
class Soudh:
def __init__(self):
self.proxy_pool = ProxyPool(flag=False)
self.proxy_ip = self.proxy_pool.get()
conn = MongoClient("10.10.101.22", 27017)
self.db = conn.spider
def get_suppliers(self):
def thread_go(page_url):
html_analyse = HtmlAnalyse(page_url)
while True:
try:
bs_content = html_analyse.get_bs_contents()
break
except Exception as e:
print(e)
ul_tag = bs_content.find(name="div",
attrs={"class": "leftbox comlist"})
li_tags = ul_tag.find_all(name="li")
corporations = []
for li_tag in li_tags:
corporation = li_tag.text.strip()
corporation_dict = {
"corporation": corporation,
"province_url": province_url,
"page_url": page_url,
"状态": "未完成"
}
corporations.append(corporation)
col = self.db.All_Company_Name
col.insert(corporation_dict)
print(corporations)
return corporations
for province_id in range(1, 36):
province_url = "http://www.soudh.com/province-" + str(
province_id) + ".html"
html_analyse = HtmlAnalyse(province_url)
bs_content = html_analyse.get_bs_contents()
page_tag = bs_content.find(name="span", text=re.compile(r'当前为'))
page_count = int(re.match(r'.*?共(\d+)页', page_tag.text).group(1))
page_urls = map(
lambda page_num: province_url[:-5] + "-" + str(page_num) +
".html", range(1, page_count + 1))
#
# for page_url in page_urls:
# thread_go(page_url)
threading_pool = ThreadingPool()
threading_pool.multi_thread(thread_go, page_urls)
class MouserGo:
def __init__(self):
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
self.mouser_host_url = "http://www.mouser.cn"
self.my_session = requests.session()
def get_all_category(self):
while True:
try:
self.my_session.proxies.update(self.proxy_ip)
my_headers = {'Connection': 'Keep-Alive',
'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.101 Safari/537.36',
"Host": "www.mouser.cn", "Upgrade-Insecure-Requests": "1",
"Referer": "http://www.mouser.cn/Electronic-Components/", }
self.my_session.headers.update(my_headers)
res = self.my_session.get("http://www.mouser.cn/Electronic-Components/")
if res.status_code != 200:
print(res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
bs_content = BeautifulSoup(res.content, "lxml")
category_url_tags = bs_content.find_all(name="a", attrs={"class": "SearchResultsSubLevelCategory"})
if not category_url_tags:
print(sys._getframe().f_code.co_name, "category_url_tag is None")
continue
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
multi_category_structures = []
for category_url_tag in category_url_tags:
url = self.mouser_host_url + category_url_tag.get("href")[2:]
single_category_structures = self.get_detail_category(url)
multi_category_structures += single_category_structures
return multi_category_structures
def get_detail_category(self, url):
while True:
try:
detail_headers = {'Connection': 'Keep-Alive',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.101 Safari/537.36',
"Host": "www.mouser.cn", "Upgrade-Insecure-Requests": "1",
"Referer": "http://www.mouser.cn/Electronic-Components/", }
self.my_session.proxies.update(self.proxy_ip)
self.my_session.headers.update(detail_headers)
res = self.my_session.get(url, timeout=20)
if res.status_code != 200:
print(res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
bs_content = BeautifulSoup(res.content, "lxml")
first_category_tag = bs_content.find(name="a",
id="ctl00_ContentMain_bc_rptrBreadcrumbs_ctl01_lnkBreadcrumb")
if not first_category_tag:
self.proxy_pool.remove(self.proxy_ip)
print("None, go on")
self.proxy_ip = self.proxy_pool.get()
continue
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
first_category_name = first_category_tag.text
second_category_tag = bs_content.find(name="a", id="ctl00_ContentMain_bc_rptrBreadcrumbs_ctl02_lnkBreadcrumb")
second_category_name = second_category_tag.text
third_category_tag = bs_content.find(name="a", id="ctl00_ContentMain_bc_rptrBreadcrumbs_ctl03_lnkBreadcrumb")
if third_category_tag:
third_category_name = third_category_tag.text
else:
third_category_name = second_category_name
detail_category_tags = bs_content.find_all(name="div", attrs={"class": "div-cat-title"})
category_structures = []
if detail_category_tags:
pre_category_url = re.match(r"(.+)/_/.+/$", url).group(1)
for detail_category_tag in detail_category_tags:
forth_category_tag = detail_category_tag.a
forth_category_name = forth_category_tag.text
forth_category_url = pre_category_url + forth_category_tag.get("href")[5:]
component_count = detail_category_tag.span.span.text.replace(",", "")
category_structure = (
first_category_name, second_category_name, third_category_name, forth_category_name,
forth_category_url,
component_count)
category_structures.append(category_structure)
else:
forth_category_name = third_category_name
forth_category_url = url
component_count_tag = bs_content.find(name="span", id="ctl00_ContentMain_lblProductCount")
component_count = component_count_tag.text.replace("(", "").replace(")", "").replace(",", "")
category_structure = (
first_category_name, second_category_name, third_category_name, forth_category_name, forth_category_url,
component_count)
category_structures.append(category_structure)
print(category_structures)
return category_structures
def category_to_csv(self, category_structure):
with open("..\\Mouser.csv", "w", encoding="utf-8") as f:
for category_structure in category_structure:
modify_category_structure = []
for category_name in category_structure:
modify_category_name = category_name.replace(",", "，")
modify_category_structure.append(modify_category_name)
line = (",".join(modify_category_structure)) + "\n"
f.write(line.encode().decode())
def read_from_csv(self):
csv_categories = []
with open("..\\Mouser.csv", "r", encoding="utf-8") as f:
read = csv.reader(f)
for line in read:
print(line)
csv_categories.append(line)
return csv_categories
def thread_go(self, category_tree):
first_category_name = category_tree[0].replace("\ufeff", "")
second_category_name = str(category_tree[1:-2])
url, component_count = category_tree[-2:]
if component_count == 1:
return
my_headers = {'Connection': 'Keep-Alive',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36',
"Host": "www.mouser.cn", "Upgrade-Insecure-Requests": "1", }
for page_num in range(0, int(component_count), 25):
page_url = url + "?No=" + str(page_num)
count = 0
while True:
try:
self.my_session.headers.update(my_headers)
self.my_session.proxies.update(self.proxy_ip)
res = self.my_session.get(page_url, timeout=20)
if res.status_code != 200:
print(res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
bs_content = BeautifulSoup(res.content, "lxml")
component_tags = bs_content.find(name="table", attrs={"class": "SearchResultsTable"}).find_all(
name="tr", attrs={"class": re.compile(r"SearchResult")})
break
except Exception as e:
count += 1
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
if count > 20:
self.proxy_pool._refresh()
table_header_tags = component_tags[0].find_all(name="th")[11:]
for component_tag in component_tags[2:]:
td_tags = component_tag.find_all(name="td")
try:
rough_component_code = td_tags[3].text.strip()
no = len(rough_component_code)
for num, code_str in enumerate(rough_component_code):
if code_str == "\n":
no = num
break
component_code = rough_component_code[:no]
except Exception as e:
print("component code is None", e)
continue
try:
component_img = self.mouser_host_url + td_tags[1].find(name="img").get("src").replace("/sm/",
"/images/")
except:
component_img = ""
try:
rough_attach = td_tags[6].find(name="a", text=re.compile(r".*数据表"))
component_attach = rough_attach.get("href")
if "http" not in component_attach:
component_attach = ""
except Exception as e:
print("pdf is none", page_url, component_code)
component_attach = ""
# if not component_img:
# continue
try:
component_brand = td_tags[4].a.text
except Exception as e:
print(sys._getframe().f_code.co_name, e)
continue
component = (
component_code, component_brand, first_category_name, second_category_name, page_url,
component_attach,
component_img)
count = 0
try:
rohs_tag = td_tags[10]
except Exception as e:
print(e)
continue
property_key_values = []
if rohs_tag.text == "详细信息":
key_value = ("RoHS", "Yes")
property_key_values.append(key_value)
len_heads = len(table_header_tags)
if len_heads:
for name_tag, property_tag in zip(table_header_tags, td_tags[-len_heads:]):
property_name = name_tag.text.strip()
property_value = property_tag.text.strip()
key_value = (property_name, property_value)
property_key_values.append(key_value)
while True:
try:
orcl_conn = OracleSave(1000002)
orcl_conn.component_insert(component)
for key_value in property_key_values:
orcl_conn.properties_insert(key_value)
orcl_conn.commit()
orcl_conn.conn.close()
break
except Exception as e:
print(e)
count += 1
# if count > 3:
# break
def get_page_url(self, category_trees):
pages_category = []
for category_tree in category_trees:
first_category_name = category_tree[0].replace("\ufeff", "")
second_category_name = str(category_tree[1:-2])
url, component_count = category_tree[-2:]
if component_count == 1:
continue
for page_num in range(0, int(component_count), 25):
page_url = url + "?No=" + str(page_num)
page_category = (first_category_name, second_category_name, page_url)
pages_category.append(page_category)
return pages_category
def page_thread_go(self, page_category):
first_category_name, second_category_name, page_url = page_category
count = 0
my_headers = {'Connection': 'Keep-Alive',
'Accept-Language': 'zh-CN,zh;q=0.8',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36',
"Host": "www.mouser.cn", "Upgrade-Insecure-Requests": "1", }
while True:
try:
self.my_session.headers.update(my_headers)
self.my_session.proxies.update(self.proxy_ip)
res = self.my_session.get(page_url, timeout=20)
if res.status_code != 200:
print(res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
bs_content = BeautifulSoup(res.content, "lxml")
component_tags = bs_content.find(name="table", attrs={"class": "SearchResultsTable"}).find_all(
name="tr", attrs={"class": re.compile(r"SearchResult")})
break
except Exception as e:
count += 1
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
if count > 20:
self.proxy_pool._refresh()
table_header_tags = component_tags[0].find_all(name="th")[11:]
for component_tag in component_tags[2:]:
td_tags = component_tag.find_all(name="td")
try:
rough_component_code = td_tags[3].text.strip()
no = len(rough_component_code)
for num, code_str in enumerate(rough_component_code):
if code_str == "\n":
no = num
break
component_code = rough_component_code[:no]
except Exception as e:
print("component code is None", e)
continue
try:
component_img = self.mouser_host_url + td_tags[1].find(name="img").get("src").replace("/sm/",
"/images/")
except:
component_img = ""
try:
rough_attach = td_tags[6].find(name="a", text=re.compile(r".*数据表"))
component_attach = rough_attach.get("href")
if "http" not in component_attach:
component_attach = ""
except Exception as e:
print("pdf is none", page_url, component_code)
component_attach = ""
# if not component_img:
# continue
try:
component_brand = td_tags[4].a.text
except Exception as e:
print(sys._getframe().f_code.co_name, e)
continue
component = (
component_code, component_brand, first_category_name, second_category_name, page_url,
component_attach,
component_img)
count = 0
try:
rohs_tag = td_tags[10]
except Exception as e:
print(e)
continue
property_key_values = []
if rohs_tag.text == "详细信息":
key_value = ("RoHS", "Yes")
property_key_values.append(key_value)
len_heads = len(table_header_tags)
if len_heads:
for name_tag, property_tag in zip(table_header_tags, td_tags[-len_heads:]):
property_name = name_tag.text.strip()
property_value = property_tag.text.strip()
key_value = (property_name, property_value)
property_key_values.append(key_value)
while True:
try:
orcl_conn = OracleSave(1000002)
orcl_conn.component_insert(component)
for key_value in property_key_values:
orcl_conn.properties_insert(key_value)
orcl_conn.commit()
orcl_conn.conn.close()
break
except Exception as e:
print("database save exception", e)
count += 1
class RsGo:
def __init__(self):
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
def get_second_category(self):
while True:
try:
html_analyse = HtmlAnalyse(
"http://china.rs-online.com/web/c/pcb-prototyping/pcb-cleaning/",
proxy=self.proxy_ip)
bs_content = html_analyse.get_bs_contents()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
first_categories = bs_content.find_all(
name="div", attrs={"class": "horizontalMenu sectionUp"})
second_categories = []
for first_category in first_categories:
first_category_name = first_category.span.text
ul_tags = first_category.find_all(name="ul",
attrs={"class": "column1"})
for ul_tag in ul_tags:
li_tags = ul_tag.find_all(name="li")
for li_tag in li_tags:
second_category_url = Rs_Pre_Url + li_tag.a.get("href")
second_category_name = li_tag.a.text.replace(
li_tag.a.span.text, "").strip()
second_category = (first_category_name,
second_category_name,
second_category_url)
second_categories.append(second_category)
return second_categories
def get_page_url(self, second_category):
first_category_name, second_category_name, second_category_url = second_category
while True:
try:
html_analyse = HtmlAnalyse(second_category_url,
proxy=self.proxy_ip)
bs_content = html_analyse.get_bs_contents()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
ul_tag = bs_content.find(name="ul", attrs={"class": "brcategories"})
third_category_tags = ul_tag.find_all(
name="div", attrs={"class": "rsGARealEstate"})
for third_category_tag in third_category_tags:
third_category_name = third_category_tag.a.text
third_category_url = Rs_Pre_Url + third_category_tag.a.get("href")
while True:
try:
html_analyse = HtmlAnalyse(third_category_url,
proxy=self.proxy_ip)
bs_content = html_analyse.get_bs_contents()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
try:
page_tag = bs_content.find(name="div",
attrs={
"class": "viewProdDiv"
}).text
except Exception as e:
print(third_category_url, e, "找不到page_tag")
continue
flag = re.match(r".*?共(.*?)个", page_tag)
page_count = int(int(flag.group(1).strip()) / 20 + 1)
for page_num in range(int(page_count)):
page_url = third_category_url + "?pn=" + str(page_num + 1)
while True:
try:
html_analyse = HtmlAnalyse(page_url,
proxy=self.proxy_ip)
bs_content = html_analyse.get_bs_contents()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
component_url_tags = bs_content.find_all(
name="a", attrs={"class": "tnProdDesc"})
page_attributes = []
for component_url_tag in component_url_tags:
component_url = Rs_Pre_Url + component_url_tag.get("href")
union_category_name = second_category_name + "---" + third_category_name
page_attribute = (first_category_name, union_category_name,
component_url)
page_attributes.append(page_attribute)
#
threadingpool = ThreadingPool(4)
threadingpool.multi_process(self.thread_go, page_attributes)
# for page_attribute in page_attributes:
# self.thread_go(page_attribute)
continue
def thread_go(self, page_attributes):
cc_unit, cc_kiname, cc_url = page_attributes
html_analyse = HtmlAnalyse(cc_url)
while True:
try:
bs_content = html_analyse.get_bs_contents()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
brand_tag = bs_content.find(name="span", attrs={"itemprop": "brand"})
name_tag = bs_content.find(name="span", attrs={"itemprop": "mpn"})
if not brand_tag or not name_tag:
return
cc_brandname = brand_tag.text.strip()
cc_code = name_tag.text.strip()
img_tag = bs_content.find(name="img", attrs={"itemprop": "image"})
if not img_tag:
cc_img = ""
else:
cc_img = Rs_Pre_Url + img_tag.get("src")
attach_tag = bs_content.find(
name="a",
attrs={"onclick": re.compile(r"window\.open\('http://docs")})
if not attach_tag:
cc_attach = ""
else:
attach_name = attach_tag.get("onclick")
try:
cc_attach = re.match(r"window\.open\('(.*?\.pdf)'\)",
attach_name).group(1)
except Exception as e:
print(sys._getframe().f_code.co_name, e)
cc_attach = ""
component = (cc_code, cc_brandname, cc_unit, cc_kiname, cc_url,
cc_attach, cc_img)
# 器件属性
while True:
try:
orcl_conn = OracleSave(1000005)
orcl_conn.component_insert(component)
component_properties = []
tr_tags = bs_content.find_all(
name="tr", attrs={"class": re.compile(r"dr-table-row")})
for tr_tag in tr_tags:
td_tags = tr_tag.find_all(name="td")
parameter_name = td_tags[1].text
parameter_value = td_tags[2].text
component_property = (parameter_name, parameter_value)
component_properties.append(component_property)
orcl_conn.properties_insert(component_property)
orcl_conn.commit()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
finally:
orcl_conn.conn.close()
def csv_write(self, category_structures):
with open("..\\Rs-online.csv", "w", encoding="utf-8") as f:
for category_structure in category_structures:
modify_category_structure = []
for structure_name in category_structure:
modify_structure_name = structure_name.replace(",", "，")
modify_category_structure.append(modify_structure_name)
line = (",".join(modify_category_structure)) + "\n"
f.write(line.encode().decode())
def get_csv_categories(self):
while True:
try:
html_analyse = HtmlAnalyse(
"http://china.rs-online.com/web/c/pcb-prototyping/pcb-cleaning/",
proxy=self.proxy_ip)
bs_content = html_analyse.get_bs_contents()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
first_categories = bs_content.find_all(
name="div", attrs={"class": "horizontalMenu sectionUp"})
third_categories = []
for first_category in first_categories:
first_category_name = first_category.span.text
ul_tags = first_category.find_all(name="ul",
attrs={"class": "column1"})
for ul_tag in ul_tags:
li_tags = ul_tag.find_all(name="li")
for li_tag in li_tags:
second_category_url = Rs_Pre_Url + li_tag.a.get("href")
second_category_name = li_tag.a.text.replace(
li_tag.a.span.text, "").strip()
while True:
try:
html_analyse = HtmlAnalyse(second_category_url,
proxy=self.proxy_ip)
bs_content = html_analyse.get_bs_contents()
ul_tag = bs_content.find(
name="ul", attrs={"class": "brcategories"})
break
except Exception as e:
print(sys._getframe().f_code.co_name, e,
second_category_url)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
if ul_tag:
third_category_tags = ul_tag.find_all(
name="div", attrs={"class": "rsGARealEstate"})
for third_category_tag in third_category_tags:
third_category_name = third_category_tag.a.text
third_category_url = Rs_Pre_Url + third_category_tag.a.get(
"href")
third_category = (first_category_name,
second_category_name,
third_category_name,
third_category_url)
print(third_category)
third_categories.append(third_category)
else:
third_category = (first_category_name,
second_category_name,
second_category_name,
second_category_url)
print(third_category)
third_categories.append(third_category)
return third_categories
class PdfDownload:
def __init__(self, task_code):
self.task_code = task_code
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
self.path = "..\\tmp\\"
if not os.path.exists(self.path):
os.mkdir(self.path)
self.db = OracleConnection()
def write(self):
with open(self.path + "text.txt", 'w') as f:
f.write('aaa')
def get_urls_from_db(self):
cursor = self.db.conn.cursor()
cursor.execute(
"update product$component set cmp_attach=null where cmp_attach='None'"
)
# 去除与之前爬取pdf重复的
cursor.execute(
"merge into product$component_crawl a using ( select cc_b2c_attach,cc_attach from product$component_crawl where cc_b2c_attach is not null group by cc_b2c_attach,cc_attach ) b on (a.cc_attach = b.cc_attach ) when matched then update set a.cc_b2c_attach = b.cc_b2c_attach where a.cc_b2c_attach is null"
)
cursor.execute(
"select distinct cc_attach from product$component_crawl where cc_b2c_attach is null and cc_attach is not null and cc_task=(select cct_id from product$component_crawl_task where cct_taskid='{}')"
.format(self.task_code))
pdf_datas = cursor.fetchall()
cursor.close()
self.db.conn.commit()
self.db.conn.close()
pdf_urls = []
for pdf_data in pdf_datas:
# if re.match(r'.*?\.pdf', pdf_data[0]):
pdf_urls.append(pdf_data[0])
return pdf_urls
def download(self, pdf_url):
filename = self.path + str(random.random()) + '.pdf'
try:
html_analyse = HtmlAnalyse(pdf_url, proxy=self.proxy_ip)
html_analyse.download(filename)
print("下载完成。。。")
except Exception as e:
print(e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
self.download(pdf_url)
return filename
def upload(self, filename, pdf_url):
try:
with open(filename, 'rb') as file:
res = requests.post("http://10.10.100.200:9999/file/upload",
files={'file': file})
res_j = res.json()
print("上传完成")
db = OracleConnection()
cursor = db.conn.cursor()
cursor.execute(
"update product$component_crawl set cc_b2c_attach='{}' where cc_attach='{}'"
.format(res_j['path'], pdf_url))
cursor.close()
db.conn.commit()
db.conn.close()
except Exception as e:
print(e)
self.upload(filename, pdf_url)
def go(self):
pdf_urls = self.get_urls_from_db()
for pdf_url in pdf_urls:
filename = self.download(pdf_url)
self.upload(filename, pdf_url)
def thread_go(self):
pdf_urls = self.get_urls_from_db()
def thread(pdfurl):
filename = self.download(pdfurl)
self.upload(filename, pdfurl)
threading_pool = ThreadingPool()
threading_pool.multi_thread(thread, pdf_urls)
class MLCC1Detail:
def __init__(self, second_class):
self.first_class_name, self.second_class_name, self.url, self.page_count = second_class
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
def get_class_components(self):
page_urls = map(lambda num: self.url + "&p=" + str(num),
range(1, self.page_count + 1))
return page_urls
def get_page_components(self, page_url):
my_headers = First_Headers
my_cookies = First_Cookies
while True:
try:
my_session = requests.session()
my_session.headers.update(my_headers)
my_session.cookies.update(my_cookies)
my_session.proxies.update(self.proxy_ip)
pass
except Exception as e:
print(sys._getframe().f_code.co_name, e)
time.sleep(1)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
try:
res = my_session.get(page_url, timeout=15)
content = res.content.decode()
except Exception as e:
print(e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
if res.status_code == 200 and content:
break
else:
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
bs_content = BeautifulSoup(content, "lxml")
product_tags = bs_content.find_all(
name="li", attrs={"data-id": re.compile(r'\d+')})
many_components_properties = []
for product_tag in product_tags:
all_p_tags = product_tag.find_all(name="p")
try:
product_code = all_p_tags[0].b.a.text
except:
continue
product_brand = all_p_tags[0].find(name='a', id='brand_n').text
product_parameter = all_p_tags[0].find(name="a", id="params").text
try:
product_pdf = product_tag.find(name="a",
attrs={
"data-id": "pdf"
}).get("href")
if "http://" not in product_pdf:
product_pdf = Pre_Url + product_pdf
except Exception as e:
print(sys._getframe().f_code.co_name, e)
product_pdf = ""
component = (product_code, product_brand, self.first_class_name,
self.second_class_name, page_url, product_pdf, "null")
properties = [
("product_parameter", product_parameter),
]
try:
product_details = all_p_tags[3].find_all(name="span")
except Exception as e:
print(e)
product_details = ""
for product_detail in product_details:
detail_text = product_detail.text.split("：")
try:
key_value = (detail_text[0], detail_text[1])
except Exception as e:
print(e)
key_value = (detail_text[0], "")
properties.append(key_value)
component_properties = (component, properties)
many_components_properties.append(component_properties)
return many_components_properties
class SearchList:
def __init__(self):
self.proxy_pool = ProxyPool()
self.page_count = ""
def get_all_urls(self, key_word):
while True:
self.proxy_ip = self.proxy_pool.get()
my_session = requests.session()
tianyan_headers = TianYan_Headers
tianyan_headers["Referer"] = (
"http://www.tianyancha.com/search?key=" + key_word +
"&checkFrom=searchBox").encode().decode('latin-1')
my_session.headers.update(tianyan_headers)
try:
my_session.proxies.update(self.proxy_ip)
except Exception as e:
print(e)
time.sleep(1)
continue
try:
first_res = my_session.get(
"http://www.tianyancha.com/tongji/" + key_word +
".json?random=" +
str(round(time.time(), 3)).replace(".", ""),
timeout=15)
first_content = first_res.content
first_data_v = eval(first_content)["data"]["v"]
except Exception as e:
print(e)
self.proxy_pool.remove(self.proxy_ip)
continue
if first_res.status_code != 200 or not first_content:
self.proxy_pool.remove(self.proxy_ip)
continue
first_token = re.match(r".*?token=(.*?);.*?",
str(bytes(eval(first_data_v)))).group(1)
my_cookie = TianYan_Cookies
my_cookie["token"] = first_token
my_session.cookies.update(my_cookie)
try:
real_res = my_session.get("http://www.tianyancha.com/search/" +
key_word + ".json?",
timeout=15)
content = real_res.content.decode()
except Exception as e:
print(e)
self.proxy_pool.remove(self.proxy_ip)
continue
if first_res.status_code != 200 or not content:
self.proxy_pool.remove(self.proxy_ip)
continue
break
try:
json_list = json.loads(content)
brief_companies = json_list["data"]
except Exception as e:
print(e)
return
while True:
try:
conn = MongoClient("10.10.101.22", 27017)
if not brief_companies:
print(key_word, "无数据")
col = conn.spider.All_Company_Name
col.update({"corporation": key_word},
{'$set': {
"状态": "无数据"
}},
multi=True)
conn.close()
return
for brief_company in brief_companies:
company_id = brief_company["id"]
detail_company_url = "http://www.tianyancha.com/company/" + str(
company_id)
detail_company = {
"company_id": company_id,
"url": detail_company_url,
"状态": "未完成"
}
detail_col = conn.spider.All_Company_Info
detail_col.update({"company_id": company_id},
{'$set': detail_company},
upsert=True)
col = conn.spider.All_Company_Name
col.update({"corporation": key_word}, {'$set': {
"状态": "已完成"
}},
multi=True)
print(key_word, "已完成")
conn.close()
break
except Exception as e:
print(e)
continue
class DetailInfo:
def __init__(self):
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
def get_detail(self, url):
while True:
my_session = requests.session()
my_headers = TianYan_Detail_Headers
my_headers["Referer"] = url
my_session.headers.update(TianYan_Detail_Headers)
try:
my_session.proxies.update(self.proxy_ip)
except Exception as e:
print(e)
time.sleep(1)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
try:
first_res = my_session.get(url.replace("company", "tongji") + ".json?random=" + str(
round(time.time(), 3)).replace(".", ""), timeout=15)
first_content = first_res.content
first_data_v = eval(first_content)["data"]["v"]
except Exception as e:
print(e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
if first_res.status_code != 200 or not first_content:
print(first_res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
first_token = re.match(r".*?token=(.*?);.*?", str(bytes(eval(first_data_v)))).group(1)
another = re.match(r".*?\{return'(.*?)'", str(bytes(eval(first_data_v)))).group(1)
def get_wtf(another):
data = another.split(",")
secret = "6,b,t,f,2,z,l,5,w,h,q,i,s,e,c,p,m,u,9,8,y,k,j,r,x,n,-,0,3,4,d,1,a,o,7,v,g".split(",")
wtf = ""
for i in data:
wtf += str(secret[int(i)])
return wtf
first_wtf = get_wtf(another)
my_cookie = TianYan_Detail_Cookies
my_cookie["token"] = first_token
my_cookie["_utm"] = first_wtf
my_headers["CheckError"] = "check"
my_headers["Referer"] = url
my_session.cookies.update(my_cookie)
my_session.headers.update(my_headers)
try:
real_res = my_session.get(url + ".json", timeout=15)
content = real_res.content.decode()
except Exception as e:
print(e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
if real_res.status_code != 200 or not content:
print(real_res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
try:
json_list = json.loads(content)
brief_companies = json_list["data"]
break
except Exception as e:
print(e)
conn = MongoClient("10.10.101.22", 27017)
col = conn.spider.All_Company_Info
if not brief_companies:
print(url, "无数据")
col.update({"url": url}, {'$set': {"状态": "无数据"}})
else:
while True:
try:
col.update({"url": url}, {'$set': {"data": brief_companies, "状态": "已完成"}})
print(url, "已完成")
break
except Exception as e:
print(e)
conn.close()
return
class Category:
def __init__(self):
self.proxy_pool = ProxyPool()
def get_categories(self):
main_url = "http://www.chip1stop.com/web/CHN/zh/dispClassSearchTop.do"
self.proxy_ip = self.proxy_pool.get()
while True:
try:
html_analsye = HtmlAnalyse(main_url, proxy=self.proxy_ip)
bs_content = html_analsye.get_bs_contents()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
dl_tags = bs_content.find_all(
name="dl", attrs={"class": "categoryListDl clearfix"})
second_categories = []
for dl_tag in dl_tags:
first_directory_name = dl_tag.dt.text
second_directory_tags = dl_tag.find_all(name="dd")
for second_directory_tag in second_directory_tags:
rough_second_directory_name = second_directory_tag.text
second_directory_name = re.match(
r"(.*?)\[", rough_second_directory_name).group(1).strip()
second_directory_url = "http://www.chip1stop.com/web/CHN/zh" + second_directory_tag.span.a.get(
"href")[1:]
second_directory = (first_directory_name,
second_directory_name,
second_directory_url)
second_categories.append(second_directory)
return second_categories
def get_product_list(self):
categories = self.get_categories()
form_data = {
"nextSearchIndex": "0",
"dispPageNo": "1",
"dispNum": "100",
"type": "page"
}
request_headers = {
"Accept": "text/html, */*; q=0.01",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.8",
"Content-Type": "application/x-www-form-urlencoded",
"Origin": "http://www.chip1stop.com",
"Host": "www.chip1stop.com",
"Proxy-Connection": "keep-alive",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.14 Safari/537.36",
"X-Requested-With": "XMLHttpRequest",
}
request_cookie = {
"CK_005": "jS1czThT76C51HOUQ42UtQ06TsvRnzI105VoKAixt4s=",
"CK_002": "aYWM1+FztffTlWgoCLG3iw==",
"CK_001": "v1gP31jjkR0=",
"CK_007": "cPDwiM71wuQ=",
"CK_006": "kQp2UYR7V1g=",
"CK_008": "i0dI70Swgcs=",
"WMONID": "VvpmCoTZsss",
"_gat": "1",
"_ga": "GA1.2.1422864444.1488415703",
"JSESSIONIDVERSION": "2f633173:8",
"JSESSIONID": "b7d640d0a05a7885ab3cab0168cf.ap2",
"JREPLICA": "c1-instance6",
"id":
"27e37541744912b7||t=1486458155|et=730|cs=002213fd4869c45d604be72033",
"Referer": "https://www.chip1stop.com/web/CHN/zh/login.do"
}
complete_form_data = {
"nextSearchIndex": "0",
"dispPageNo": "1",
"dispNum": "25",
"rental": "false",
"partSameFlg": "false",
"subWinSearchFlg": "false",
"used": "false",
"newProductFlg": "false",
"newProudctHandlingFlg": "false",
"newSameDayShippedFlg": "false",
"eventId": "0001",
"searchType": "2",
"dispAllFlg": "true",
}
def thread_go(page_no):
print("Page:", page_no)
page_parts = range(0, 25, 5)
for page_part in page_parts:
print("Part:", page_part)
# def thread_go(page_part):
complete_form_data['nextSearchIndex'] = page_part
complete_form_data['dispPageNo'] = page_no
complete_form_data['type'] = "page"
detail_url = second_category_url + "&dispPageNo=%d" % page_no
while True:
try:
my_session.cookies.update(request_cookie)
res = my_session.post(detail_url,
data=complete_form_data,
proxies=self.proxy_ip,
timeout=20)
print(res.status_code)
if res.status_code == 200:
content = res.content.decode()
bs_content = BeautifulSoup(content, "lxml")
tr_tags = bs_content.find_all(name="tr")[1:]
if tr_tags:
break
else:
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
tr_tags = bs_content.find_all(name="tr")[1:]
if not tr_tags:
continue
# 数据库连接
orcl_conn = OracleSave(1000001)
for tr_tag in tr_tags:
try:
code = tr_tag.td.find(name="p",
attrs={
"class": "text14pt2 bold"
}).text.strip()
except Exception as e:
print(e)
continue
chip1stop_code = tr_tag.td.find(name="p",
attrs={
"class": "text10"
}).text.strip()
print(chip1stop_code)
maker = tr_tag.td.find(name="p",
attrs={
"class": "text10 wordBreak"
}).text.strip()
pdf_url = tr_tag.find(
name="a",
attrs={
"href":
re.compile(
r"http://download\.siliconexpert\.com/pdfs")
})
if pdf_url:
pdf_url = pdf_url.get("href")
component = (code, maker, first_category_name,
second_category_name, second_category_url,
pdf_url, None)
orcl_conn.component_insert(component)
property_tags = tr_tag.find_all(name="td")[6:-1]
for property_name, property_tag in zip(
property_names, property_tags):
if property_name == '购买/询价':
continue
property_value = property_tag.text
if property_value:
property_value = property_value.strip()
single_property = (property_name, property_value)
orcl_conn.properties_insert(single_property)
orcl_conn.commit()
orcl_conn.conn.close()
# def thread_go(page_no):
for category in categories:
first_category_name, second_category_name, second_category_url = category
while True:
try:
my_session = requests.session()
my_session.headers.update(request_headers)
self.proxy_ip = self.proxy_pool.get()
res = my_session.post(second_category_url,
data=form_data,
proxies=self.proxy_ip,
timeout=10)
print(res.status_code)
if res.status_code == 200:
break
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
except Exception as e:
print(sys._getframe().f_code.co_name, e)
self.proxy_pool.remove(self.proxy_ip)
content = res.content.decode()
bs_content = BeautifulSoup(content, "lxml")
products_count = bs_content.find(name="span",
attrs={
"class": "bold_red"
}).text.replace(",", "").replace(
"件", "")
table_headers_tag = bs_content.find(name="tr",
attrs={"class": "parent"})
property_name_tags = table_headers_tag.find_all(name="td")
# 器件参数名称
property_names = []
for property_name_tag in property_name_tags[6:-1]:
property_name = property_name_tag.text.strip()
property_names.append(property_name)
# 总页数
pages_count = int(int(products_count) / 25) + 1
if pages_count > 400:
pages_count = 400
# for page_no in range(1, pages_count + 1):
# ---------------------------我是分割线----------------------------
# threading_pool = ThreadingPool(10)
# threading_pool.multi_process(thread_go, list(range(1, pages_count + 1)))
for i in range(1, pages_count + 1):
thread_go(i)
class FPNewark:
def __init__(self):
self.my_session = requests.session()
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
pass
def get_category_trees(self, category_trees):
multi_category_trees = []
for category_tree in category_trees:
url = category_tree[-2]
count = 0
while True:
try:
self.my_session.proxies.update(self.proxy_ip)
res = self.my_session.get(url, timeout=20)
if res.status_code != 200:
print(res.status_code)
continue
bs_content = BeautifulSoup(res.content, "lxml")
break
except Exception as e:
count += 1
print(sys._getframe().f_code.co_name, url, e)
self.proxy_ip = self.proxy_pool.get()
if count > 100:
self.proxy_pool._refresh()
category_list = bs_content.find(name="ul",
attrs={"class": "categoryList"})
if not category_list:
print(category_tree)
multi_category_trees.append(category_tree)
continue
else:
child_category_tags = category_list.find_all(name="a")
category_trees = []
for child_category_tag in child_category_tags:
child_category_url = child_category_tag.get("href")
rough_child_category_tag = child_category_tag.text.strip()
flag = re.match(r"(.*?) \((\d+.*?)\)",
rough_child_category_tag)
child_category_name = flag.group(1)
component_count = flag.group(2).replace(",", "")
if component_count == '1':
continue
child_category = [
child_category_name, child_category_url,
component_count
]
child_category_tree = list(
category_tree)[:-2] + child_category
category_trees.append(child_category_tree)
child_categories = self.get_category_trees(category_trees)
print(child_categories)
multi_category_trees += child_categories
print("Current Count： ", len(multi_category_trees))
return multi_category_trees
def get_first_categories(self):
my_headers = Default_Header
my_headers["host"] = "www.newark.com"
my_headers["Referer"] = "http://www.newark.com/"
my_headers["Upgrade-Insecure-Requests"] = "1"
while True:
try:
self.my_session.headers.update(my_headers)
self.my_session.proxies.update(self.proxy_ip)
res = self.my_session.get(
"http://www.newark.com/browse-for-products", timeout=20)
if res.status_code != 200:
print(res.status_code)
continue
bs_content = BeautifulSoup(res.content, "lxml")
first_category_tags = bs_content.find_all(
name="ul", attrs={"categoryList"})
break
except Exception as e:
print("Part1", sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
second_pages = []
for first_category_tag in first_category_tags:
first_category_name = first_category_tag.li.h2.text.strip()
second_category_tags = first_category_tag.li.ul.find_all(name="li")
for second_category_tag in second_category_tags:
second_category_url = second_category_tag.a.get("href")
rough_second_category_name = second_category_tag.text.strip()
flag = re.match(r"(.*?) \((\d+.*?)\)",
rough_second_category_name)
second_category_name = flag.group(1)
component_count = flag.group(2).replace(",", "")
if component_count == '1':
continue
second_page = (first_category_name, second_category_name,
second_category_url, component_count)
second_pages.append(second_page)
return second_pages
def csv_write(self, category_structures):
with open("..\\Newark_test.csv", "w", encoding="utf-8") as f:
for category_structure in category_structures:
modify_category_structure = []
for structure_name in category_structure:
modify_structure_name = structure_name.replace(",", "，")
modify_category_structure.append(modify_structure_name)
line = (",".join(modify_category_structure)) + "\n"
f.write(line.encode().decode())
#
def thread_go(self, category_tree):
my_headers = Default_Header
my_headers["host"] = "www.newark.com"
my_headers["Referer"] = "http://www.newark.com/"
my_headers["Upgrade-Insecure-Requests"] = "1"
first_category_name = category_tree[0]
second_category_name = str(category_tree[1:-2])
url, component_count = category_tree[-2:]
page_count = int(int(component_count) / 25) + 1
for page_num in range(877, page_count + 1):
page_url = url + "/prl/results/" + str(page_num)
count = 0
while True:
try:
self.my_session.headers.update(my_headers)
self.my_session.proxies.update(self.proxy_ip)
res = self.my_session.get(page_url, timeout=20)
if res.status_code != 200:
print(res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
bs_content = BeautifulSoup(res.content, "lxml")
component_tags = bs_content.find(
name="table", id="sProdList").tbody.find_all(name="tr")
break
except Exception as e:
count += 1
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
if count > 10:
print(category_tree, page_url)
component_tags = []
break
if count > 100:
self.proxy_pool._refresh()
for component_tag in component_tags:
detail_table = component_tag.find(name="table",
attrs={"class": "TFtable"})
td_tags = component_tag.find_all(name="td")
try:
component_code = td_tags[1].text.strip()
except Exception as e:
print("component code is None", e)
continue
try:
component_img = td_tags[1].find(name="img",
attrs={
"class":
"productThumbnail"
}).get("src")
except:
component_img = ""
try:
rough_attach = td_tags[2].find(name="a", text="数据表")
if not rough_attach:
rough_attach = td_tags[2].find(
name="a", attrs={"class": "prodDetailsAttachment"})
component_attach = rough_attach.get("href")
if "http" not in component_attach:
component_attach = ""
except Exception as e:
component_attach = ""
try:
manufacture_description = td_tags[3].a.find_all(name="p")
component_brand = manufacture_description[0].text.strip()
component_description = manufacture_description[
1].text.strip()
except Exception as e:
component_brand = ""
print(sys._getframe().f_code.co_name, e)
continue
if not component_img and not component_attach and not component_brand:
continue
component = (component_code, component_brand,
first_category_name, second_category_name,
page_url, component_attach, component_img)
count = 0
while True:
try:
orcl_conn = OracleSave(1000003)
orcl_conn.component_insert(component)
if detail_table:
property_tags = detail_table.find_all(name="tr")
for property_tag in property_tags:
detail_td_tags = property_tag.find_all("td")
property_name = detail_td_tags[0].text.strip()
property_value = detail_td_tags[1].text.strip()
key_value = (property_name, property_value)
orcl_conn.properties_insert(key_value)
orcl_conn.commit()
orcl_conn.conn.close()
break
except Exception as e:
print(e)
count += 1
# if count > 3:
# break
def extra_go(self, category_tree):
my_headers = Default_Header
my_headers["host"] = "www.newark.com"
my_headers["Referer"] = "http://www.newark.com/"
my_headers["Upgrade-Insecure-Requests"] = "1"
first_category_name = category_tree[0]
second_category_name = str(category_tree[1:-2])
url, component_count = category_tree[-2:]
page_count = int(int(component_count) / 25) + 1
page_range = range(875, 17557)
def extra_thread(page_num):
page_url = url + "/prl/results/" + str(page_num)
count = 0
while True:
try:
self.my_session.headers.update(my_headers)
self.my_session.proxies.update(self.proxy_ip)
res = self.my_session.get(page_url, timeout=20)
if res.status_code != 200:
print(res.status_code)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
continue
bs_content = BeautifulSoup(res.content, "lxml")
component_tags = bs_content.find(
name="table", id="sProdList").tbody.find_all(name="tr")
break
except Exception as e:
count += 1
print(sys._getframe().f_code.co_name, e)
self.proxy_ip = self.proxy_pool.get()
if count > 10:
print(category_tree, page_url)
component_tags = []
break
if count > 100:
self.proxy_pool._refresh()
for component_tag in component_tags:
detail_table = component_tag.find(name="table",
attrs={"class": "TFtable"})
td_tags = component_tag.find_all(name="td")
try:
component_code = td_tags[1].text.strip()
except Exception as e:
print("component code is None", e)
continue
try:
component_img = td_tags[1].find(name="img",
attrs={
"class":
"productThumbnail"
}).get("src")
except:
component_img = ""
try:
rough_attach = td_tags[2].find(name="a", text="数据表")
if not rough_attach:
rough_attach = td_tags[2].find(
name="a", attrs={"class": "prodDetailsAttachment"})
component_attach = rough_attach.get("href")
if "http" not in component_attach:
component_attach = ""
except Exception as e:
component_attach = ""
try:
manufacture_description = td_tags[3].a.find_all(name="p")
component_brand = manufacture_description[0].text.strip()
component_description = manufacture_description[
1].text.strip()
except Exception as e:
component_brand = ""
print(sys._getframe().f_code.co_name, e)
continue
if not component_img and not component_attach and not component_brand:
continue
component = (component_code, component_brand,
first_category_name, second_category_name,
page_url, component_attach, component_img)
count = 0
while True:
try:
orcl_conn = OracleSave(1000003)
orcl_conn.component_insert(component)
if detail_table:
property_tags = detail_table.find_all(name="tr")
for property_tag in property_tags:
detail_td_tags = property_tag.find_all("td")
property_name = detail_td_tags[0].text.strip()
property_value = detail_td_tags[1].text.strip()
key_value = (property_name, property_value)
orcl_conn.properties_insert(key_value)
orcl_conn.commit()
orcl_conn.conn.close()
break
except Exception as e:
print(e)
count += 1
# if count > 3:
# break
extra_threading = ThreadingPool(8)
extra_threading.multi_process(extra_thread, page_range)
def read_from_csv(self):
csv_categories = []
with open("..\\Newark_test.csv", "r", encoding="utf-8") as f:
read = csv.reader(f)
for line in read:
print(line)
csv_categories.append(line)
return csv_categories
class DownloadUpload:
def __init__(self):
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
pass
def file_download(self, url, file_type, file_name=str(random.random())):
download_dir_path = "..\\download_files\\"
if not os.path.exists(download_dir_path):
os.mkdir(download_dir_path)
download_file_path = download_dir_path + file_name + file_type
if os.path.exists(download_file_path):
return
try_count = 0
while True:
try:
download_file_path = download_dir_path + str(random.random()) + file_type
# html_analyse = HtmlAnalyse(url, proxy=self.proxy_ip)
my_session = requests.session()
my_headers = {'Connection': 'Keep-Alive',
'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
"User-Agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36',
"host": "www.newark.com", "Referer": "http://www.newark.com/",
"Upgrade-Insecure-Requests": "1"}
my_session.headers.update(my_headers)
my_session.proxies.update(self.proxy_ip)
res = my_session.get(url)
if res.status_code != 200 or not res.content:
print(sys._getframe().f_lineno)
continue
with open(download_file_path, 'wb') as f:
f.write(res.content)
print("File Download Success !!")
break
except Exception as e:
print(sys._getframe().f_code.co_name, url, e)
try_count += 1
# if try_count > 2 and "https" in url:
# return
# if try_count > 5:
# return
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
# download_file_path = download_dir_path + str(random.random()) + file_type
return download_file_path
def file_upload(self, local_file_path):
if not local_file_path:
return
while True:
try:
with open(local_file_path, "rb") as f:
res = requests.post(File_Server_Url, files={'file': f})
if res.status_code == 200:
res_j = res.json()
break
except Exception as e:
print(sys._getframe().f_code.co_name, e)
server_file_path = res_j["path"]
print("File Server Upload Success !!")
return server_file_path
def download_upload(self, url, file_type):
download_file_path = self.file_download(url, file_type)
server_file_path = self.file_upload(download_file_path)
return server_file_path
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.8",
"Content-Type": "application/x-www-form-urlencoded",
"Origin": "http://www.chip1stop.com",
"Referer":
"http://www.chip1stop.com/web/CHN/zh/search.do?classCd=040101&classLv=3&subWinSearchFlg=false&searchType=2&dispAllFlg=true&searchFlg=false",
"Host": "www.chip1stop.com",
"Proxy-Connection": "keep-alive",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.14 Safari/537.36",
"X-Requested-With": "XMLHttpRequest",
}
if __name__ == "__main__":
proxy_pool = ProxyPool()
proxy_ip = proxy_pool.get()
my_session = requests.session()
my_session.headers.update(request_headers)
while True:
try:
res = my_session.post(
"http://www.chip1stop.com/web/CHN/zh/search.do?",
data=form_data,
proxies=proxy_ip)
print(res.status_code)
break
except Exception as e:
print(e)
proxy_pool.remove(proxy_ip)
proxy_ip = proxy_pool.get()
content = res.content.decode()
class PdfDownload1:
def __init__(self, task_code):
self.task_code = task_code
self.proxy_pool = ProxyPool()
self.proxy_ip = self.proxy_pool.get()
self.path = "D:\pdf\\"
if not os.path.exists(self.path):
os.mkdir(self.path)
self.db = OracleConnection()
def write(self):
with open(self.path + "text.txt", 'w') as f:
f.write('aaa')
def get_urls_from_db(self):
cursor = self.db.conn.cursor()
cursor.execute(
"update product$component set cmp_attach=null where cmp_attach='None'"
)
# 去除与之前爬取pdf重复的
cursor.execute(
"merge into product$component_crawl a using ( select cc_b2c_attach,cc_attach from product$component_crawl where cc_b2c_attach is not null group by cc_b2c_attach,cc_attach ) b on (a.cc_attach = b.cc_attach ) when matched then update set a.cc_b2c_attach = b.cc_b2c_attach where a.cc_b2c_attach is null"
)
cursor.execute(
"select distinct cc_attach from product$component_crawl where cc_b2c_attach is null and cc_attach is not null and cc_task=(select cct_id from product$component_crawl_task where cct_taskid='{}')"
.format(self.task_code))
pdf_datas = cursor.fetchall()
cursor.close()
self.db.conn.commit()
self.db.conn.close()
pdf_urls = []
for pdf_data in pdf_datas:
# if re.match(r'.*?\.pdf', pdf_data[0]):
pdf_urls.append(pdf_data[0])
return pdf_urls
def download(self, pdf_url):
content_list = re.match(r'downloadLinkClick\((.*?)\);return false',
a).group(1).split(",")
filename = content_list[0].replace("'", "")
url = "http://ds.yuden.co.jp/TYCOMPAS/cs/detail.do?mode=download&fileName=" + filename
isSeriesData = content_list[1]
isProductsData = content_list[2]
isProductsDataGraph = content_list[3]
DownloadForm = {
"action": "detail.do",
"classificationID": "AE",
"fileName": filename,
"isSeriesData": isSeriesData,
"isProductsData": isProductsData,
"isProductsDataGraph": isProductsDataGraph
}
html_analyse = HtmlAnalyse(url)
html_analyse.post_download(
data=DownloadForm,
path="I:\PythonPrj\StandardSpider\DataAnalyse\\NewRules\\a.pdf")
filename = self.path + str(random.random()) + '.pdf'
try:
html_analyse = HtmlAnalyse(url, proxy=self.proxy_ip)
html_analyse.download(filename)
print("下载完成。。。")
except Exception as e:
print(e)
self.proxy_pool.remove(self.proxy_ip)
self.proxy_ip = self.proxy_pool.get()
self.download(pdf_url)
return filename
def upload(self, filename, pdf_url):
try:
with open(filename, 'rb') as file:
res = requests.post("http://10.10.100.200:9999/file/upload",
files={'file': file})
res_j = res.json()
print("上传完成")
db = OracleConnection()
cursor = db.conn.cursor()
cursor.execute(
"update product$component_crawl set cc_b2c_attach='{}' where cc_attach='{}'"
.format(res_j['path'], pdf_url))
cursor.close()
db.conn.commit()
db.conn.close()
except Exception as e:
print(e)
self.upload(filename, pdf_url)
def go(self):
pdf_urls = self.get_urls_from_db()
for pdf_url in pdf_urls:
filename = self.download(pdf_url)
self.upload(filename, pdf_url)
def thread_go(self):
pdf_urls = self.get_urls_from_db()
def thread(pdfurl):
filename = self.download(pdfurl)
self.upload(filename, pdfurl)
threading_pool = ThreadingPool()
threading_pool.multi_thread(thread, pdf_urls)